Data Scientist - Credit

This role sits at the intersection of analytics, engineering, and business decisioning. You’ll help modernize how we build, deploy, and monitor credit models — ensuring our models not only perform well analytically but are also scalable, explainable, and production-ready. Duties & Responsibilities - Strengthen Credit Risk Modeling and Credit Predictability

Build and enhance credit risk models that improve credit predictability and portfolio performance.

Conduct exploratory data analysis and experiment tracking to identify key risk drivers and optimize model outcomes.

Partner closely with Credit Strategy, Implementation, and Feature Platform teams to connect model insights directly to decision flows.

Keep our modeling framework adaptive to changing credit dynamics and economic conditions.

Duties & Responsibilities - Bridge Data Science and MLOps for Reliable Model Delivery

Own Python project structure, CI/CD setup, and end-to-end testing for reliable model delivery.

Collaborate with MLOps and Feature Platform teams to maintain model pipelines (e.g., Metaflow, SageMaker, or equivalent orchestration frameworks).

Support model deployment, validation, and performance consistency in production.

Drive standardization, automation, and reproducibility across the modeling lifecycle.

Duties & Responsibilities - Support Model Monitoring and Governance

Expand and maintain monitoring frameworks for production models.

Support compliance reviews, validation exercises, and performance monitoring (e.g., PSI/CSI analysis, reject inference).

Maintain audit-ready documentation and ensure transparency across model development and production processes.

Requirements

Bachelor’s degree in a quantitative field (Statistics, Mathematics, Computer Science, Engineering, Data Science, or related).

Master’s or PhD preferred.

Strong understanding of the model lifecycle (EDA, modeling, evaluation, deployment).

Proficiency in Python (pandas, scikit-learn, etc.) and SQL.

Experience with Metaflow or similar orchestration frameworks (e.g., Flyte, ZenML, SageMaker Pipelines).

Familiarity with cloud environments (AWS preferred).

Experience with model deployment (FastAPI + Docker or similar).

Understanding of version control (Git/GitHub), unit testing (pytest), and modern Python tooling (e.g., uv, poetry).

Proven accountability, communication, and work ethic — able to deliver high-quality work on time with minimal oversight.

Nice to Have

Background in credit risk modeling or lending-related ML applications (e.g., underwriting, loss prediction, fraud detection).

Experience integrating ML solutions with decision systems or APIs.

Familiarity with model monitoring frameworks or model governance processes.

Comfort working in cross-functional teams and presenting technical results to non-technical stakeholders.