Machine Learning Engineer II (Underwriting ML)

Affirm is hiring a Machine Learning Engineer II for its Underwriting ML team, working remotely across the US. You'll develop and maintain machine learning systems that drive real-time transaction decisions, evaluating repayment risk and expected value at checkout. The role involves collaborating with ML engineers, platform teams, and cross-functional stakeholders to move models from concept through production and ongoing monitoring as market conditions shift.

Responsibilities

• Develop and iterate on underwriting prediction models using approaches for tabular and sequential data
• Build and scale feature pipelines and training datasets from internal and third-party data sources, coordinating with data and platform teams
• Prototype new modeling approaches and features, run offline experiments, and deploy high-performing solutions into production with appropriate risk controls
• Productionize models by integrating into batch and real-time decision systems, optimizing for reliability, latency, and operational robustness
• Monitor model and data health, define retraining and backtesting workflows, and instrument alerting systems
• Partner with Engineering, Risk Analytics, Product, and ML Platform teams to define requirements, evaluate technical tradeoffs, and communicate findings to technical and non-technical stakeholders

Requirements

• 2+ years of experience as a machine learning engineer, or a PhD in a relevant field
• Strong Python proficiency and demonstrated ability to write production-quality code
• Experience building and evaluating classification models, preferably with gradient-boosted decision tree libraries (LightGBM, XGBoost, CatBoost, or equivalent)
• Experience with a deep learning framework (PyTorch preferred)
• Experience with distributed data processing or parallel compute frameworks (Spark preferred; Ray, Dask, or similar)
• Experience with ML lifecycle tooling for training orchestration, experimentation, and model monitoring (Kubeflow, Airflow, MLflow, or equivalent platforms)
• Proficiency using AI-powered developer tools (Claude Code, Cursor, or similar) as part of daily development workflows
• Ability to translate business scenarios into solutions spanning multiple software components and execute with clear, tested, and maintainable code
• Comfortable working within and navigating large codebases