Data Scientist - (Knowledge Graph & Identity)

{
  "content_hash": "525022e18704c51097bd24dde953a5c8286ff9d9839775ba5bc98d860460e7be",
  "source_hash": "145e79ffb586363713aa528ea877b1c2334ed65ee9495d028dce8ac8a98db028",
  "last_changed_at": "2026-06-06T07:56:57.164Z",
  "active_status": "active"
}

{
  "language": "en",
  "location": {
    "raw": "San Francisco, California",
    "city": "San Francisco",
    "region": "CA",
    "country": "United States",
    "is_remote": false,
    "confidence": 0.85
  },
  "salary_max": 200000,
  "salary_min": 120000,
  "inferred_at": "2026-06-06T07:56:57.103Z",
  "launch_scope": {
    "reason": "english_us_canada",
    "included": true,
    "language": "en",
    "location": {
      "raw": "San Francisco, California",
      "city": "San Francisco",
      "region": "CA",
      "country": "United States",
      "is_remote": false,
      "confidence": 0.85
    },
    "countries": [
      "United States"
    ]
  },
  "remote_policy": null,
  "salary_period": "year",
  "workplace_type": "on_site",
  "salary_currency": "PLN"
}

{}

{
  "lists": [
    {
      "text": "What You'll Do:",
      "content": "\n<li>Contribute to data science projects across the full lifecycle — from problem scoping and exploratory analysis through to model development and deployment — with support from senior team members</li>\n<li>Develop and test Python and PySpark code on Databricks, building clean, documented, and reusable solutions for knowledge graph and identity challenges</li>\n<li>Apply core ML techniques — regression, classification, clustering, and model evaluation ,to complex, high-volume datasets, and begin exploring advanced methods such as entity resolution, embedding-based matching, and semantic similarity</li>\n<li>Support MLOps practices including experiment tracking, pipeline orchestration, and model monitoring, adopting DataOps and reproducibility standards throughout</li>\n<li>Break down project requirements into well-scoped tasks with clear acceptance criteria, and contribute to technical documentation covering problem statements, approaches, and metrics</li>\n<li>Collaborate cross-functionally with product, engineering, and operations — translating business requirements into technical tasks and participating in design reviews and working groups</li>\n"
    },
    {
      "text": "Who You Are: ",
      "content": "\n<li>Bachelor's degree required in Statistics, Data Science, Computer Science, Mathematics or a related quantitative field; Master's strongly preferred</li>\n<li>1 to 2 years of hands-on data science experience with demonstrated ability to own and deliver complex, multi-sprint projects independently</li>\n<li>Python with production-quality code, testing, and documentation; strong SQL and PySpark for billion-row datasets</li>\n<li>Databricks workflows, Delta Lake, and job orchestration; working knowledge of cloud platforms (AWS or GCP)</li>\n<li>Solid command of core ML — regression, classification, clustering, model evaluation, and experimental design — applied to complex, high-volume data</li>\n<li>Proficiency with MLOps practices: experiment tracking, pipeline orchestration (Airflow), and reproducible model deployment</li>\n<li>Exposure to modern AI methodologies: RAG systems, LLM-augmented models, vector databases, and semantic search</li>\n<li>Strong communicator — able to translate technical work into clear documentation, user stories, and cross-functional conversations</li>\n"
    },
    {
      "text": "Preferred skills:",
      "content": "\n<li>Hands-on experience with knowledge graph construction, entity resolution, or semantic data modeling (RDF, OWL, SPARQL, or equivalent graph frameworks)</li>\n<li>Familiarity with probabilistic record linkage, identity graph approaches, or embedding-based entity matching at scale</li>\n<li>Experience with causal inference methods (A/B testing, synthetic control, uplift modeling)</li>\n<li>Experience with deduplication, enrichment, or web-to-TV linkage problems</li>\n<li>Background in media, ad tech, or measurement — TV viewership (ACR/STB data), digital audience modeling, cross-platform measurement (linear + CTV/OTT), or identity resolution in privacy-constrained environments</li>\n<li>Familiarity with the measurement and identity vendor landscape (Nielsen, Comscore, LiveRamp, The Trade Desk</li>\n"
    }
  ],
  "country": "US",
  "createdAt": 1773136555891,
  "updatedAt": null,
  "categories": {
    "team": "Data Science & Analytics",
    "location": "San Francisco, California",
    "commitment": "International Full Time Employee",
    "department": "Engineering",
    "allLocations": [
      "San Francisco, California"
    ]
  },
  "salaryRange": {
    "max": 200000,
    "min": 120000,
    "currency": "PLN",
    "interval": "per-year-salary"
  },
  "workplaceType": "onsite"
}