Senior Data Scientist

What you’ll do

• Design and improve graph-based approaches for identity resolution across devices, households, and identifiers which improve match quality, coverage, and stability across a rapidly changing identity landscape.
• Use Scala, Spark, SQL, and cloud-native tools to analyze large identity datasets, build models, and productionize data science workflows.
• Contribute production-grade code to shared repositories, using strong engineering practices to build clear, scalable, and maintainable systems.
• Define validation strategies and measure model performance and business impact on targeting, measurement, and attribution.
• Help shape the team’s approach to identity science and partner across Engineering, Product, and Analytics to deliver production-ready solutions.
• Leverage LLMs, AI editors (Cursor, Copilot, Claude Code), and agentic workflows to accelerate research, prototyping, documentation, testing, and iteration.
• Apply privacy-by-design principles to ensure identity science work is auditable, compliant, and aligned with governance standards.

What you’ll bring

• 5+ years of experience in data science, machine learning, or applied research working with large-scale datasets in production.
• Strong experience building identity graphs, entity resolution systems, record linkage pipelines, or related graph-based matching systems.
• Deep expertise in Scala, Spark, SQL, and/or Python for distributed processing, model development, and experimentation.
• Strong foundation in applied statistics, machine learning, graph algorithms, clustering, probabilistic matching, and model evaluation.
• Experience productionizing data science solutions in partnership with engineering, including testing, monitoring, and reproducibility.
• Experience mentoring data scientists and helping define technical direction across a team.
• Comfortable with AI-assisted workflows and modern development tools.