Data Scientist- Hybrid (3 times per week)

{
  "content_hash": "3ca5ef9cbe5e7eac053f7ddbc8848c850850a7d367a3a34384b797daed84e995",
  "source_hash": "a983beb3ab3101f7daf08c84061a9e9c97df7ee784722e6b43467f4a8e8946e7",
  "last_changed_at": "2026-05-30T05:44:15.676Z",
  "active_status": "active"
}

{
  "language": "en",
  "location": {
    "raw": "New York, NY",
    "city": "New York",
    "region": "NY",
    "country": "United States",
    "is_remote": false,
    "confidence": 0.9
  },
  "salary_max": null,
  "salary_min": null,
  "inferred_at": "2026-06-06T19:36:53.676Z",
  "launch_scope": {
    "reason": "jazzhr_production_catalog",
    "included": true,
    "location": {
      "raw": "New York, NY",
      "city": "New York",
      "region": "NY",
      "country": "United States",
      "is_remote": false,
      "confidence": 0.9
    },
    "countries": [
      "United States"
    ]
  },
  "remote_policy": "hybrid",
  "salary_period": null,
  "workplace_type": "hybrid",
  "salary_currency": null
}

{}

{
  "detail": {
    "url": "https://fusemachines.applytojob.com/apply/jobs/details/pYO5KHk85I?&",
    "heading": "Data Scientist- Hybrid (3 times per week)",
    "html_title": "JazzHR » Job Listings",
    "canonical_url": "https://jobs.fusemachines.com/apply/pYO5KHk85I/Data-Scientist-Hybrid-3-Times-Per-Week",
    "description_html": "<span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"display:none;\"> </span></span></span><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>About Fusemachines</strong><br>Founded in 2013, Fusemachines is a global provider of enterprise AI products and services, on a mission to democratize AI. Leveraging proprietary AI Studio and AI Engines, the company helps drive the clients’ AI Enterprise Transformation, regardless of where they are in their Digital AI journeys. With offices in North America, Asia, and Latin America, Fusemachines provides a suite of enterprise AI offerings and specialty services that allow organizations of any size to implement and scale AI. Fusemachines serves companies in industries such as retail,  manufacturing, and government.</span></span></h3><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Fusemachines continues to actively pursue the mission of democratizing AI for the masses by providing high-quality AI education in underserved communities and helping organizations achieve their full potential with AI.</span></span></h3><strong>Salary Range:</strong> US$ 140,000-170,000/year<br> <p style=\"line-height:1.3800027272727273;margin-bottom:13px;\"><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"font-variant:normal;white-space:pre-wrap;\"><span style=\"color:#000000;\"><span style=\"background-color:#ffffff;\"><span style=\"font-weight:700;\"><span style=\"font-style:normal;\"><span style=\"text-decoration:none;\">Important: Immigration Sponsorship Policy<br><br>This position is not elegible for employment visa sponsorship or transfer sponsorship now or in the future.</span></span></span></span></span></span></span></span></p><ul><li style=\"list-style-type:disc;\"><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"font-variant:normal;white-space:pre-wrap;\"><span style=\"color:#000000;\"><span style=\"background-color:#ffffff;\"><span style=\"font-weight:400;\"><span style=\"font-style:normal;\"><span style=\"text-decoration:none;\">Direct Company Sponsorship: Such as H-1B, J-1, or TN visas.</span></span></span></span></span></span></span></span></li><li style=\"list-style-type:disc;\"><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"font-variant:normal;white-space:pre-wrap;\"><span style=\"color:#000000;\"><span style=\"background-color:#ffffff;\"><span style=\"font-weight:400;\"><span style=\"font-style:normal;\"><span style=\"text-decoration:none;\">Employer of Record: Listing Fusemachines as the immigration employer on any government documentation.</span></span></span></span></span></span></span></span></li><li style=\"list-style-type:disc;\"><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"font-variant:normal;white-space:pre-wrap;\"><span style=\"color:#000000;\"><span style=\"background-color:#ffffff;\"><span style=\"font-weight:400;\"><span style=\"font-style:normal;\"><span style=\"text-decoration:none;\">Written Documentation: Providing letters or other support for any work authorization (e.g., OPT, STEM OPT, CPT).</span></span></span></span></span></span></span></span></li></ul> <h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Role Overview</strong></span></span></h3><p><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">We’re hiring a mid-to-senior Machine Learning Engineer / Data Scientist to build and deploy machine learning solutions that drive measurable business impact. You’ll work across the ML lifecycle—from problem framing and data exploration to model development, evaluation, deployment, and monitoring—often in partnership with client stakeholders and internal delivery teams.</span></span></p><p><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">You should be strong in core data science and applied machine learning, comfortable working with real-world data, and capable of turning modeling work into production-ready systems.</span></span></p><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Key Responsibilities</strong></span></span></h3><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Problem Framing & Stakeholder Partnership</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Translate business questions into ML problem statements (classification, regression, time series forecasting, clustering, anomaly detection, recommendation, etc.).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Collaborate with stakeholders to define success metrics, evaluation plans, and practical constraints (latency, interpretability, cost, data availability).</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Data Analysis & Feature Engineering</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Use SQL and Python to extract, join, and analyze data from relational databases and data warehouses.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Perform data profiling, missingness analysis, leakage checks, and exploratory analysis to guide modeling choices.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Build robust feature pipelines (aggregation, encoding, scaling, embeddings where appropriate) and document assumptions.</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Model Development (Core ML)</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Train and tune supervised learning models for tabular data (e.g., logistic/linear models, tree-based methods, gradient boosting such as XGBoost/LightGBM/CatBoost, and neural nets for structured data).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Apply strong tabular modeling practices: handling missing data, categorical encoding, leakage prevention, class imbalance strategies, calibration, and robust cross-validation.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Build time series models (statistical and ML/DL approaches) and validate with proper backtesting.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Apply clustering and segmentation techniques (k-means, hierarchical, DBSCAN, Gaussian mixtures) and evaluate stability and usefulness.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Apply statistics in practice (hypothesis testing, confidence intervals, sampling, experiment design) to support inference and decision-making.</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Deep Learning</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Build and train deep learning models using PyTorch or TensorFlow/Keras.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Use best practices for training (regularization, calibration, class imbalance handling, reproducibility, sound train/val/test design).</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Evaluation, Explainability, and Iteration</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Choose appropriate metrics (AUC/F1/PR, RMSE/MAE/MAPE, calibration, lift, and business KPIs) and create evaluation reports.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Perform error analysis and interpretation (feature importance/SHAP, cohort slicing) and iterate based on evidence.</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Productionization & MLOps (Project-Dependent)</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Package models for deployment (batch scoring pipelines or real-time APIs) and collaborate with engineers on integration.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Implement practical MLOps: versioning, reproducible training, automated evaluation, monitoring for drift/performance, and retraining plans.</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Documentation & Communication</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Communicate tradeoffs and recommendations clearly to technical and non-technical stakeholders.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Create documentation and lightweight demos that make results actionable.</span></span></li></ul></li></ul><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Success in This Role Looks Like</span></span></h3><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">You deliver models that perform well and move business metrics (revenue lift, cost reduction, risk reduction, improved forecast accuracy, operational efficiency).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Your work is reproducible and production-aware: clear data lineage, robust evaluation, and a credible path to deployment/monitoring.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Stakeholders trust your judgment in selecting methods and communicating uncertainty honestly.</span></span></li></ul><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Required Qualifications</strong></span></span></h3><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">3–8 years of experience in data science, machine learning engineering, or applied ML (mid-to-senior).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Strong Python skills for data analysis and modeling (pandas/numpy/scikit-learn or equivalent).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Strong SQL skills (joins, window functions, aggregation, performance awareness).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Solid foundation in statistics (hypothesis testing, uncertainty, bias/variance, sampling) and practical experimentation mindset.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Hands-on experience across multiple model types, including:</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Classification & regression</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Time series forecasting</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Clustering/segmentation</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience with deep learning in PyTorch or TensorFlow/Keras.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Strong problem-solving skills: ability to work with ambiguous goals and messy data.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Clear communication skills and ability to translate analysis into decisions.</span></span></li></ul><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Preferred Qualifications</strong></span></span></h3><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience with Databricks for applied ML (e.g., Spark, Delta Lake, MLflow, Databricks Jobs/Workflows).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience deploying models to production (APIs, batch pipelines) and maintaining them over time (monitoring, retraining).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience with orchestration tools (Airflow, Prefect, Dagster) and modern data stacks (Snowflake/BigQuery/Redshift/Databricks).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience with cloud platforms (AWS/GCP/Azure/IBM) and containerization (Docker).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience with responsible AI and governance best practices (privacy/PII handling, auditability, access controls).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Consulting or client-facing delivery experience.</span></span></li></ul><p><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Certifications (Strong Plus)</strong><br>Candidates with at least one relevant certification are especially encouraged to apply:</span></span></p><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Cloud certifications: AWS, Google Cloud, Microsoft Azure, or IBM (data/AI/ML tracks)</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Databricks certifications (Data Scientist, Data Engineer, or related)</span></span></li></ul><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Nice-to-Have</strong></span></span></h3><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Causal inference experience (e.g., quasi-experimental methods, propensity scores, uplift/heterogeneous treatment effects, experimentation beyond A/B tests).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Agentic development experience: designing and evaluating agentic workflows (tool use, planning, memory/state, guardrails) and integrating them into products.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Deep familiarity with agentic coding tools and workflows for accelerated product development (e.g., AI-assisted IDEs, code agents, automated testing/refactoring, repo-aware assistants), including strong judgment on quality, security, and maintainability.</span></span></li></ul><div style=\"list-style-type:disc;\"><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><em><em>Fusemachines is an Equal Opportunities Employer, committed to diversity and inclusion. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or any other characteristic protected by applicable federal, state, or local laws.</em></em></span></span><br><br><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"display:none;\"> </span></span></span></div>",
    "description_text": "About Fusemachines\nFounded in 2013, Fusemachines is a global provider of enterprise AI products and services, on a mission to democratize AI. Leveraging proprietary AI Studio and AI Engines, the company helps drive the clients’ AI Enterprise Transformation, regardless of where they are in their Digital AI journeys. With offices in North America, Asia, and Latin America, Fusemachines provides a suite of enterprise AI offerings and specialty services that allow organizations of any size to implement and scale AI. Fusemachines serves companies in industries such as retail,  manufacturing, and government.\n Fusemachines continues to actively pursue the mission of democratizing AI for the masses by providing high-quality AI education in underserved communities and helping organizations achieve their full potential with AI.\n Salary Range:  US$ 140,000-170,000/year\n  Important: Immigration Sponsorship Policy\nThis position is not elegible for employment visa sponsorship or transfer sponsorship now or in the future.\n Direct Company Sponsorship: Such as H-1B, J-1, or TN visas.\n Employer of Record: Listing Fusemachines as the immigration employer on any government documentation.\n Written Documentation: Providing letters or other support for any work authorization (e.g., OPT, STEM OPT, CPT).\n   Role Overview\n We’re hiring a mid-to-senior Machine Learning Engineer / Data Scientist to build and deploy machine learning solutions that drive measurable business impact. You’ll work across the ML lifecycle—from problem framing and data exploration to model development, evaluation, deployment, and monitoring—often in partnership with client stakeholders and internal delivery teams.\n You should be strong in core data science and applied machine learning, comfortable working with real-world data, and capable of turning modeling work into production-ready systems.\n Key Responsibilities\n Problem Framing & Stakeholder Partnership Translate business questions into ML problem statements (classification, regression, time series forecasting, clustering, anomaly detection, recommendation, etc.).\n Collaborate with stakeholders to define success metrics, evaluation plans, and practical constraints (latency, interpretability, cost, data availability).\n Data Analysis & Feature Engineering Use SQL and Python to extract, join, and analyze data from relational databases and data warehouses.\n Perform data profiling, missingness analysis, leakage checks, and exploratory analysis to guide modeling choices.\n Build robust feature pipelines (aggregation, encoding, scaling, embeddings where appropriate) and document assumptions.\n Model Development (Core ML) Train and tune supervised learning models for tabular data (e.g., logistic/linear models, tree-based methods, gradient boosting such as XGBoost/LightGBM/CatBoost, and neural nets for structured data).\n Apply strong tabular modeling practices: handling missing data, categorical encoding, leakage prevention, class imbalance strategies, calibration, and robust cross-validation.\n Build time series models (statistical and ML/DL approaches) and validate with proper backtesting.\n Apply clustering and segmentation techniques (k-means, hierarchical, DBSCAN, Gaussian mixtures) and evaluate stability and usefulness.\n Apply statistics in practice (hypothesis testing, confidence intervals, sampling, experiment design) to support inference and decision-making.\n Deep Learning Build and train deep learning models using PyTorch or TensorFlow/Keras.\n Use best practices for training (regularization, calibration, class imbalance handling, reproducibility, sound train/val/test design).\n Evaluation, Explainability, and Iteration Choose appropriate metrics (AUC/F1/PR, RMSE/MAE/MAPE, calibration, lift, and business KPIs) and create evaluation reports.\n Perform error analysis and interpretation (feature importance/SHAP, cohort slicing) and iterate based on evidence.\n Productionization & MLOps (Project-Dependent) Package models for deployment (batch scoring pipelines or real-time APIs) and collaborate with engineers on integration.\n Implement practical MLOps: versioning, reproducible training, automated evaluation, monitoring for drift/performance, and retraining plans.\n Documentation & Communication Communicate tradeoffs and recommendations clearly to technical and non-technical stakeholders.\n Create documentation and lightweight demos that make results actionable.\n Success in This Role Looks Like\n You deliver models that perform well and move business metrics (revenue lift, cost reduction, risk reduction, improved forecast accuracy, operational efficiency).\n Your work is reproducible and production-aware: clear data lineage, robust evaluation, and a credible path to deployment/monitoring.\n Stakeholders trust your judgment in selecting methods and communicating uncertainty honestly.\n Required Qualifications\n 3–8 years of experience in data science, machine learning engineering, or applied ML (mid-to-senior).\n Strong Python skills for data analysis and modeling (pandas/numpy/scikit-learn or equivalent).\n Strong SQL skills (joins, window functions, aggregation, performance awareness).\n Solid foundation in statistics (hypothesis testing, uncertainty, bias/variance, sampling) and practical experimentation mindset.\n Hands-on experience across multiple model types, including: Classification & regression\n Time series forecasting\n Clustering/segmentation\n Experience with deep learning in PyTorch or TensorFlow/Keras.\n Strong problem-solving skills: ability to work with ambiguous goals and messy data.\n Clear communication skills and ability to translate analysis into decisions.\n Preferred Qualifications\n Experience with Databricks for applied ML (e.g., Spark, Delta Lake, MLflow, Databricks Jobs/Workflows).\n Experience deploying models to production (APIs, batch pipelines) and maintaining them over time (monitoring, retraining).\n Experience with orchestration tools (Airflow, Prefect, Dagster) and modern data stacks (Snowflake/BigQuery/Redshift/Databricks).\n Experience with cloud platforms (AWS/GCP/Azure/IBM) and containerization (Docker).\n Experience with responsible AI and governance best practices (privacy/PII handling, auditability, access controls).\n Consulting or client-facing delivery experience.\n Certifications (Strong Plus)\nCandidates with at least one relevant certification are especially encouraged to apply:\n Cloud certifications: AWS, Google Cloud, Microsoft Azure, or IBM (data/AI/ML tracks)\n Databricks certifications (Data Scientist, Data Engineer, or related)\n Nice-to-Have\n Causal inference experience (e.g., quasi-experimental methods, propensity scores, uplift/heterogeneous treatment effects, experimentation beyond A/B tests).\n Agentic development experience: designing and evaluating agentic workflows (tool use, planning, memory/state, guardrails) and integrating them into products.\n Deep familiarity with agentic coding tools and workflows for accelerated product development (e.g., AI-assisted IDEs, code agents, automated testing/refactoring, repo-aware assistants), including strong judgment on quality, security, and maintainability.\n Fusemachines is an Equal Opportunities Employer, committed to diversity and inclusion. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or any other characteristic protected by applicable federal, state, or local laws.",
    "jsonld_jobposting": {
      "url": "https://jobs.fusemachines.com/apply/pYO5KHk85I/Data-Scientist-Hybrid-3-Times-Per-Week",
      "@type": "JobPosting",
      "title": "Data Scientist- Hybrid (3 times per week)",
      "@context": "http://schema.org/",
      "baseSalary": {
        "@type": "MonetaryAmount",
        "value": {
          "@type": "QuantitativeValue",
          "maxValue": 170000,
          "minValue": 140000,
          "unitText": "YEAR"
        },
        "currency": "USD"
      },
      "datePosted": "2026-05-13",
      "description": "<span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"display:none;\"> </span></span></span><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>About Fusemachines</strong><br>Founded in 2013, Fusemachines is a global provider of enterprise AI products and services, on a mission to democratize AI. Leveraging proprietary AI Studio and AI Engines, the company helps drive the clients’ AI Enterprise Transformation, regardless of where they are in their Digital AI journeys. With offices in North America, Asia, and Latin America, Fusemachines provides a suite of enterprise AI offerings and specialty services that allow organizations of any size to implement and scale AI. Fusemachines serves companies in industries such as retail,  manufacturing, and government.</span></span></h3><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Fusemachines continues to actively pursue the mission of democratizing AI for the masses by providing high-quality AI education in underserved communities and helping organizations achieve their full potential with AI.</span></span></h3><strong>Salary Range:</strong> US$ 140,000-170,000/year<br> <p style=\"line-height:1.3800027272727273;margin-bottom:13px;\"><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"font-variant:normal;white-space:pre-wrap;\"><span style=\"color:#000000;\"><span style=\"background-color:#ffffff;\"><span style=\"font-weight:700;\"><span style=\"font-style:normal;\"><span style=\"text-decoration:none;\">Important: Immigration Sponsorship Policy<br><br>This position is not elegible for employment visa sponsorship or transfer sponsorship now or in the future.</span></span></span></span></span></span></span></span></p><ul><li style=\"list-style-type:disc;\"><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"font-variant:normal;white-space:pre-wrap;\"><span style=\"color:#000000;\"><span style=\"background-color:#ffffff;\"><span style=\"font-weight:400;\"><span style=\"font-style:normal;\"><span style=\"text-decoration:none;\">Direct Company Sponsorship: Such as H-1B, J-1, or TN visas.</span></span></span></span></span></span></span></span></li><li style=\"list-style-type:disc;\"><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"font-variant:normal;white-space:pre-wrap;\"><span style=\"color:#000000;\"><span style=\"background-color:#ffffff;\"><span style=\"font-weight:400;\"><span style=\"font-style:normal;\"><span style=\"text-decoration:none;\">Employer of Record: Listing Fusemachines as the immigration employer on any government documentation.</span></span></span></span></span></span></span></span></li><li style=\"list-style-type:disc;\"><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"font-variant:normal;white-space:pre-wrap;\"><span style=\"color:#000000;\"><span style=\"background-color:#ffffff;\"><span style=\"font-weight:400;\"><span style=\"font-style:normal;\"><span style=\"text-decoration:none;\">Written Documentation: Providing letters or other support for any work authorization (e.g., OPT, STEM OPT, CPT).</span></span></span></span></span></span></span></span></li></ul> <h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Role Overview</strong></span></span></h3><p><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">We’re hiring a mid-to-senior Machine Learning Engineer / Data Scientist to build and deploy machine learning solutions that drive measurable business impact. You’ll work across the ML lifecycle—from problem framing and data exploration to model development, evaluation, deployment, and monitoring—often in partnership with client stakeholders and internal delivery teams.</span></span></p><p><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">You should be strong in core data science and applied machine learning, comfortable working with real-world data, and capable of turning modeling work into production-ready systems.</span></span></p><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Key Responsibilities</strong></span></span></h3><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Problem Framing & Stakeholder Partnership</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Translate business questions into ML problem statements (classification, regression, time series forecasting, clustering, anomaly detection, recommendation, etc.).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Collaborate with stakeholders to define success metrics, evaluation plans, and practical constraints (latency, interpretability, cost, data availability).</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Data Analysis & Feature Engineering</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Use SQL and Python to extract, join, and analyze data from relational databases and data warehouses.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Perform data profiling, missingness analysis, leakage checks, and exploratory analysis to guide modeling choices.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Build robust feature pipelines (aggregation, encoding, scaling, embeddings where appropriate) and document assumptions.</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Model Development (Core ML)</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Train and tune supervised learning models for tabular data (e.g., logistic/linear models, tree-based methods, gradient boosting such as XGBoost/LightGBM/CatBoost, and neural nets for structured data).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Apply strong tabular modeling practices: handling missing data, categorical encoding, leakage prevention, class imbalance strategies, calibration, and robust cross-validation.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Build time series models (statistical and ML/DL approaches) and validate with proper backtesting.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Apply clustering and segmentation techniques (k-means, hierarchical, DBSCAN, Gaussian mixtures) and evaluate stability and usefulness.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Apply statistics in practice (hypothesis testing, confidence intervals, sampling, experiment design) to support inference and decision-making.</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Deep Learning</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Build and train deep learning models using PyTorch or TensorFlow/Keras.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Use best practices for training (regularization, calibration, class imbalance handling, reproducibility, sound train/val/test design).</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Evaluation, Explainability, and Iteration</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Choose appropriate metrics (AUC/F1/PR, RMSE/MAE/MAPE, calibration, lift, and business KPIs) and create evaluation reports.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Perform error analysis and interpretation (feature importance/SHAP, cohort slicing) and iterate based on evidence.</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Productionization & MLOps (Project-Dependent)</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Package models for deployment (batch scoring pipelines or real-time APIs) and collaborate with engineers on integration.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Implement practical MLOps: versioning, reproducible training, automated evaluation, monitoring for drift/performance, and retraining plans.</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Documentation & Communication</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Communicate tradeoffs and recommendations clearly to technical and non-technical stakeholders.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Create documentation and lightweight demos that make results actionable.</span></span></li></ul></li></ul><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Success in This Role Looks Like</span></span></h3><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">You deliver models that perform well and move business metrics (revenue lift, cost reduction, risk reduction, improved forecast accuracy, operational efficiency).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Your work is reproducible and production-aware: clear data lineage, robust evaluation, and a credible path to deployment/monitoring.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Stakeholders trust your judgment in selecting methods and communicating uncertainty honestly.</span></span></li></ul><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Required Qualifications</strong></span></span></h3><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">3–8 years of experience in data science, machine learning engineering, or applied ML (mid-to-senior).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Strong Python skills for data analysis and modeling (pandas/numpy/scikit-learn or equivalent).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Strong SQL skills (joins, window functions, aggregation, performance awareness).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Solid foundation in statistics (hypothesis testing, uncertainty, bias/variance, sampling) and practical experimentation mindset.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Hands-on experience across multiple model types, including:</span></span><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Classification & regression</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Time series forecasting</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Clustering/segmentation</span></span></li></ul></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience with deep learning in PyTorch or TensorFlow/Keras.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Strong problem-solving skills: ability to work with ambiguous goals and messy data.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Clear communication skills and ability to translate analysis into decisions.</span></span></li></ul><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Preferred Qualifications</strong></span></span></h3><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience with Databricks for applied ML (e.g., Spark, Delta Lake, MLflow, Databricks Jobs/Workflows).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience deploying models to production (APIs, batch pipelines) and maintaining them over time (monitoring, retraining).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience with orchestration tools (Airflow, Prefect, Dagster) and modern data stacks (Snowflake/BigQuery/Redshift/Databricks).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience with cloud platforms (AWS/GCP/Azure/IBM) and containerization (Docker).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Experience with responsible AI and governance best practices (privacy/PII handling, auditability, access controls).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Consulting or client-facing delivery experience.</span></span></li></ul><p><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Certifications (Strong Plus)</strong><br>Candidates with at least one relevant certification are especially encouraged to apply:</span></span></p><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Cloud certifications: AWS, Google Cloud, Microsoft Azure, or IBM (data/AI/ML tracks)</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Databricks certifications (Data Scientist, Data Engineer, or related)</span></span></li></ul><h3><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><strong>Nice-to-Have</strong></span></span></h3><ul><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Causal inference experience (e.g., quasi-experimental methods, propensity scores, uplift/heterogeneous treatment effects, experimentation beyond A/B tests).</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Agentic development experience: designing and evaluating agentic workflows (tool use, planning, memory/state, guardrails) and integrating them into products.</span></span></li><li><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\">Deep familiarity with agentic coding tools and workflows for accelerated product development (e.g., AI-assisted IDEs, code agents, automated testing/refactoring, repo-aware assistants), including strong judgment on quality, security, and maintainability.</span></span></li></ul><div style=\"list-style-type:disc;\"><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><em><em>Fusemachines is an Equal Opportunities Employer, committed to diversity and inclusion. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or any other characteristic protected by applicable federal, state, or local laws.</em></em></span></span><br><br><span style=\"font-size:14px;\"><span style=\"font-family:Arial, Helvetica, sans-serif;\"><span style=\"display:none;\"> </span></span></span></div>",
      "jobLocation": {
        "@type": "Place",
        "address": {
          "@type": "PostalAddress",
          "postalCode": "",
          "addressRegion": "NY",
          "addressLocality": "New York"
        }
      },
      "validThrough": "2026-08-11",
      "uniqueJobCode": "job_20260513143636_XBIQQVYW4PZX9ZLZ",
      "employmentType": "FULL_TIME",
      "hiringOrganization": {
        "logo": "https://s3.amazonaws.com/resumator/customer_20191108174918_T3HDEM7NCAYEC2DB/logos/20191108184722_fusemachines_logo_jpg.jpg",
        "name": "Fusemachines",
        "@type": "Organization",
        "sameAs": "https://www.fusemachines.com/"
      },
      "experienceRequirements": "Experienced"
    }
  },
  "list_job": {
    "id": "pYO5KHk85I",
    "title": "Data Scientist- Hybrid (3 times per week)",
    "detailUrl": "https://fusemachines.applytojob.com/apply/jobs/details/pYO5KHk85I?&"
  },
  "detail_errors": []
}