Data Scientist - Credit Risk & Propensity Models

Overview

Role:
Staff Data Scientist - Credit Risk & Propensity Models

Location:

San Diego, CA | Hybrid (2-3 days from office)

• Design, develop, and maintain Probability of Default (PD) and other core credit-risk models used in underwriting, portfolio management, and credit strategy
• Build and enhance propensity, conversion, and price-sensitivity models to optimize funnel performance, approval rates, and expected profitability
• Partner with Risk & Analytics leadership to translate risk appetite, growth objectives, and portfolio constraints into scalable modeling solutions
• Develop segmentation frameworks and decision logic to support differentiated credit terms, limits, and pricing across customer cohorts
• Lead model validation, performance monitoring, and stability analysis, including back-testing, drift detection, and recalibration
• Conceptualize and execute on data science research roadmap that create new insights unique to client ecosystem and drive fundamental transformation of risk models. This transformation would be the key for client to increase its market share in specific segments against incumbents.
• Collaborate with Engineering and Data teams to product ionize models, ensure reliable execution, and support ongoing model monitoring and governance
• Support experimentation, A/B testing, and test-and-learn initiatives to measure model and policy impact across the customer funnel
• Communicate model design, performance, and tradeoffs clearly to technical and non-technical stakeholders
• Contribute to documentation, model governance artifacts, and regulatory or audit-ready materials as needed

• 7+ years of hands-on experience building underwriting, credit-risk, or loss-prediction models for small-business or commercial portfolios
• Demonstrated experience developing PD, propensity, pricing, or funnel-optimization models used in live decisioning
• Experience supporting model deployment, execution, and ongoing monitoring in a production environment; MLOps experience is strongly preferred
• Statistical risk modeling
• Loss forecasting and portfolio analytics
• Limit assignment optimization
• Pricing and interest rate statistical simulations
• ML model deployment and governance
• Experimentation and A/B testing
• Strong SQL and Python proficiency; ability to work with large datasets and build reproducible analytical workflows
• Excellent communication, presentation, and story-building skills in a consulting/client-facing setup
• Demonstrated ability to lead cross-functional initiatives end-to-end and coordinate with offshore delivery teams
• Bachelors degree in a related quantitative field such as Data Science, Statistics, Mathematics, Economics, Finance, or Engineering required
• Masters degree in Data Science, Statistics, Economics, Finance, or a related quantitative discipline is a plus

Client is also open to hire junior candidates (4-5 years exp.) with similar skills at a lower band.