Director, Data Science

Role Summary
Senior data science leader who owns the strategy, roadmap, and delivery of the machine-learning and statistical models that power our consumer lending business. You will lead the development of credit risk models for underwriting and portfolio risk decisioning, while also overseeing models across fraud risk, marketing response and propensity, customer lifecycle management, collections prioritization, account management, and pricing, line, and offer optimization.

This is a hands-on, technically fluent leadership role: you will set analytical standards, build validation-ready and well-documented models, mentor and grow a team of data scientists and ML practitioners, and partner with credit, fraud, marketing, and collections leaders who own policy and business strategy. You are the modeling and data science authority who turns data into reliable, governed, production-grade models.

Key Responsibilities
Own the model development strategy and roadmap across consumer lending decisioning—credit risk underwriting and portfolio risk models, as well as fraud, marketing, customer lifecycle, collections, account management, and pricing/line/offer optimization use cases.
Lead, hire, coach, and grow a team of data scientists and ML practitioners; set technical direction, performance expectations, analytical standards, and career paths while staying hands-on enough to review code, methodology, and model design.
Direct the end-to-end model lifecycle—problem framing, data and feature engineering, model development, validation-ready documentation, deployment, monitoring, recalibration, and retirement—with clear, repeatable standards.
Drive feature engineering and the evaluation of alternative and third-party data sources (bureau, alternative credit, cash-flow/bank, device, and identity signals), quantifying lift, cost, stability, and compliance trade-offs.
Establish and govern champion/challenger experimentation, backtesting, and holdout frameworks to measure model impact on approvals, losses, response, and downstream portfolio performance.
Stand up and own model monitoring for performance, drift, and stability (PSI, KS, AUC/Gini decay, calibration) and the cadence for rebuild, recalibration, and escalation when models degrade.
Partner with model risk management and governance on documentation, validation, and audit support; ensure models meet internal model risk and regulatory expectations.
Embed fair lending and regulatory awareness into model design and feature selection (disparate impact testing, adverse action/reason codes, explainability), partnering with compliance and legal.
Partner with data engineering and decisioning-platform teams to product ionize models, evolve feature stores and data pipelines, and ensure reliable real-time and batch scoring.
Translate model outputs into actionable business strategies with credit, fraud, marketing, and collections leaders—connecting scores and segments to policy, offers, and operational actions they own.
Communicate model strategy, results, and trade-offs to executives and cross-functional partners; represent data science in prioritization, planning, and senior leadership forums.
Set and uphold analytical standards, tooling, and reproducibility practices (code review, version control, experiment tracking) across the data science function.

Qualifications
10-15 years in data science, statistical modeling, or credit risk analytics, including hands-on development of models used in production decisioning.
3+ years leading and developing data science or ML teams, with a track record of hiring, mentoring, and raising analytical standards.
Deep expertise building credit risk and portfolio decisioning models (scorecards, PD/loss models, ML classifiers/regressors) for consumer lending.
Strong hands-on Python and SQL skills and command of modern ML and statistical methods (e.g., gradient boosting, logistic/regularized regression, validation and feature selection techniques).
Experience across the full model lifecycle—feature engineering, validation-ready documentation, deployment, and ongoing monitoring of drift and performance.
Consumer lending, fintech, or financial services…