Machine Learning Engineer

Role Overview

Join Affirm’s ML Fraud team as a Machine Learning Engineer. You will build and improve machine learning systems for real-time transaction decisions, taking models from idea to production in collaboration with ML engineers, platform partners, and cross-functional stakeholders.

Key Responsibilities

• Design, develop, and improve machine learning systems for real-time transaction decisioning.
• Develop and iterate on fraud prediction models using approaches for tabular and behavioral data.
• Build feature pipelines and prototype new modeling ideas.
• Productionize models by working through the ML lifecycle and integration into production systems.
• Collaborate with stakeholders to deliver end-to-end solutions interacting with multiple software components.

Requirements

• Experience building and evaluating models for tabular classification, preferably gradient-boosted decision trees (e.g., LightGBM, XGBoost, CatBoost) or similar.
• 2+ years as an ML engineer, or a PhD in a relevant field.
• Strong Python skills and ability to write production-quality code.
• Experience with distributed data processing or parallel compute frameworks (Spark preferred; Ray/Dask or similar).
• Strong verbal and written communication skills for collaboration with a global engineering team.
• Ability to take ownership, seek feedback, and iterate based on stakeholder input.
• Experience working in a large codebase: debug, contribute, and support others through code reviews.

Nice-to-haves

• ML lifecycle tooling for training orchestration, experimentation, and model monitoring (e.g., Kubeflow, Airflow, MLflow, or equivalents).
• Experience with deep learning frameworks (notably PyTorch preferred).
• Comfort using AI-powered developer tools (e.g., Claude Code, Cursor) to accelerate development workflows.

Remote Work

• Remote-first environment (Full remote).