Design and execute data science experiments, including causal analysis, A/B tests, and offline evaluation.
Develop, evaluate, and iterate on predictive models for credit/risk scoring, revenue forecasting, and policy performance.
Own model performance and monitoring: define success metrics, investigate drift, and drive improvements to data quality and feature reliability.
Partner with Product Engineering to productionize models and analytics with emphasis on reliability, reproducibility, and maintainability.
Perform exploratory data analysis, feature engineering, and robust validation on real-world, messy data.
Communicate insights and recommendations clearly to technical and non-technical stakeholders through documentation and presentations.
Improve analytical standards, code review practices, and documentation to raise technical quality.
Mentor and support team members through pairing, feedback, and sharing best practices.

5+ years of professional experience in data science, applied machine learning, or a related quantitative role.
Strong foundations in statistics and experimentation, including hypothesis testing, causal reasoning, and evaluation design.
Proven experience building and shipping predictive models (classification, regression, time series) and measuring real-world impact.
Strong proficiency in Python and SQL and comfort working with production data workflows.
Experience defining success metrics, aligning with stakeholders, and delivering end-to-end outcomes.
Strong written communication skills and a pragmatic approach to fast-moving environments.
Experience owning model performance, monitoring for drift, and improving feature reliability.

Nice to Have

Experience with credit risk, underwriting, fraud/risk signals, or financial forecasting.
Experience with modern data tooling and warehouses such as BigQuery or Snowflake and transformation frameworks like dbt.
Familiarity with MLOps patterns (model deployment, monitoring, feature stores, orchestration) and cloud environments.
Experience working with messy third-party data sources (banking data, eCommerce platforms, marketing signals).

Senior Data Scientist

Key skills