Data Scientist (Knowledge Graph & Identity)

{
  "content_hash": "7dd129b74e1eaa54b8dec75bc6fd486c840aa597376b14d18dcad2d8deaf9954",
  "source_hash": "7185248b2a8bd72f2da03f4ac3ce82adb57075400e275c87913b8676166426dc",
  "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": "2026-06-06T07:56:57.102Z",
  "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>Own end-to-end delivery of significant data science projects — from problem scoping and approach design through to production deployment, with a focus on knowledge graph and identity solutions</li>\n<li>Make sound, independently-reasoned decisions on methodology, model selection, and evaluation; document them clearly in technical solution documents covering problem statement, approach, metrics, and timeline</li>\n<li>Lead solution design for your own initiatives; break down complex epics into well-scoped user stories with clear acceptance criteria, adopting DataOps and MLOps best practices throughout — experiment tracking, pipeline orchestration, model monitoring, and reproducibility</li>\n<li>Build production-quality Python and PySpark code on Databricks — well-tested, documented, and reusable — and implement advanced ML and AI-powered workflows including entity resolution, probabilistic record linkage, embedding-based matching, semantic similarity, and LLM-augmented pipelines</li>\n<li>Develop and maintain reusable tools, libraries, and documentation that improve team efficiency and technical standards; conduct code reviews with constructive, specific feedback that raises the bar</li>\n<li>Mentor junior data scientists on technical execution, code quality, and career development; lead internal talks or workshops on knowledge graphs, identity, or ML topics</li>\n<li>Collaborate cross-functionally with product, engineering, and operations — translate business requirements into technical specifications, partner with data engineering on scalable pipeline design, and participate in cross-functional 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>3–5 years of hands-on data science experience with demonstrated ability to own and deliver complex, multi-sprint projects independently</li>\n<li>Advanced 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<li>Demonstrated ability to mentor junior data scientists and contribute to team standards</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": 1773057428039,
  "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"
}