SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 146,000 - 225,000 / annual
Affirm is reinventing credit to make it more honest and friendly, offering buy-now-pay-later solutions without hidden fees or compounding interest. The Underwriting ML team builds and improves machine learning systems that make real-time transaction decisions, assessing repayment risk and expected value for every Affirm checkout.
In this role, you will develop and iterate on underwriting prediction models using approaches for both tabular and sequential data. You'll build and scale feature pipelines and training datasets from proprietary and third-party signals, partnering with data and platform teams as needed. You'll prototype new modeling ideas and features, run offline experiments, and drive the best-performing approaches into production with appropriate risk controls.
You'll help productionize models by integrating them into batch and/or real-time decision systems, improving reliability, latency, and operational robustness. You'll instrument and monitor model and data health, define retraining and backtesting workflows, and collaborate across Engineering, Risk Analytics, Product, and ML Platform to define requirements, evaluate tradeoffs, and communicate results to both technical and non-technical audiences.
Required qualifications include 2+ years of experience as a machine learning engineer or a PhD in a relevant field. You need strong Python skills and production-quality code experience, with expertise in classification models (preferably gradient-boosted decision trees like LightGBM, XGBoost, or CatBoost). Experience with deep learning frameworks (PyTorch preferred), distributed data processing (Spark preferred), and ML lifecycle tooling (Kubeflow, Airflow, MLflow) is essential. Proficiency with AI-powered developer tools (Claude Code, Cursor) is required. You should demonstrate the ability to take business scenarios into multi-component solutions with clear, well-tested, extensible code. A Bachelor's degree in a related field or equivalent practical experience is required.
