Machine Learning Engineer II (Servicing ML)

Affirm is building machine learning and AI systems to automate customer operations. The Servicing ML team develops models for disputes, returns, fraud, and chargebacks. This role involves building ML models and LLM-powered pipelines, collaborating with cross-functional teams, and taking projects from idea to production.

• Develop AI systems that automate dispute and chargeback handling
• Build models that automate refunds
• Build and maintain evidence extraction pipelines using LLM-powered workflows
• Prototype new modeling ideas, run offline experiments, and drive best-performing approaches into production
• Collaborate with Engineering, Servicing Operations, Product, and ML Platform

• 2+ years of experience as a machine learning engineer
• Strong Python skills and production-quality code
• Experience with gradient-boosted decision trees (LightGBM/XGBoost/CatBoost)
• Experience with LLM APIs (OpenAI, Anthropic) and orchestration frameworks (LangChain, LangGraph)
• Familiarity with document and unstructured data processing
• Experience with ML lifecycle tooling (Kubeflow, Airflow, MLflow)
• Proficient in AI-powered developer tools
• Strong communication skills