3 months ago
Base Salary
$189k - $284k/yr
Responsibilities
- Independently challenge lending, fraud, and AML model owners by reproducing results, defending acceptance thresholds, and deciding whether models are sound.
- Identify silent errors and validate them before models reach production.
- Design evaluations for rare events, shifting populations, and post-launch model drift.
- Work hands-on in unfamiliar codebases and ship production validation tooling.
- Build agentic validation tooling that orchestrates parallel agents.
- Evaluate machine learning systems end to end across features, training, serving, monitoring, and scale.
- Connect explainability and fair-lending findings on consumer credit models to model and product decisions.
- Help define validation standards for frontier production AI systems and GenAI applications.
Requirements
- A quantitative degree or equivalent experience, with senior individual-contributor depth building or validating models in a high-stakes domain such as credit, fraud, or financial crime.
- Experience with effective-challenge methodology, including reproduction, conceptual-soundness review, benchmarking, stress testing, and outcomes analysis.
- Deep applied machine learning and statistics across regression, tree ensembles, deep learning, evaluation, calibration, and generalization.
- Experience with holdout and experiment design, uncertainty reasoning, and evaluating models beyond aggregate accuracy.
- Production-quality Python, SQL on large datasets, and reproducible, tested code.
- Experience building with LLMs and agentic tools, with judgment about when their outputs can be trusted.
- Familiarity with model risk management frameworks and fair-lending standards.
- Ability to explain and defend conclusions to model owners and senior stakeholders and operate independently under ambiguity.
Benefits
- Remote-friendly within approved U.S. locations
- Remote work, medical insurance, flexible time off, retirement savings plans, and modern family planning benefits
Tech Stack
AWSDatabricksGoogle Cloud PlatformLightGBMMLflowNumPyPandaspytestPythonPyTorchscikit-learnSnowflakeSQLXGBoost
Categories
About Block
Block is one company built from many blocks, all united by the same purpose of economic empowerment. The blocks that form our foundational teams — People, Finance, Counsel, Hardware, Information Security, Platform Infrastructure Engineering, and more — provide support and guidance at the corporate level. They work across business groups and around the globe, spanning time zones and disciplines to develop inclusive People policies, forecast finances, give legal counsel, safeguard systems, nurture new initiatives, and more. Every challenge creates possibilities, and we need different perspectives to see them all. Bring yours to Block.