About the Role
On the Servicing ML team at Affirm, you will play a crucial role in building and improving machine learning and AI systems that automate customer operations, including disputes, returns, fraud, and chargebacks. Your work will ensure the best outcomes for both Affirm and its customers. You will collaborate closely with experienced ML engineers, platform partners, and cross-functional stakeholders, guiding models from ideation and prototyping through to production, and maintaining their health through robust measurement and monitoring.
What you'll do
- Develop AI systems that automate dispute and chargeback handling using structured evidence and business logic, enhancing the customer experience.
- Build models to automate refunds, ensuring faster money returns to customers.
- Construct and maintain evidence extraction pipelines that process unstructured data using LLM-powered workflows to generate structured, actionable outputs.
- Prototype new modeling concepts, conduct offline experiments, and implement the most effective approaches into production with appropriate risk controls.
- Collaborate across Engineering, Servicing Operations, Product, and ML Platform teams to define requirements, evaluate tradeoffs, and clearly communicate results to both technical and non-technical audiences.
What we look for
- A total of 2+ years of experience as a machine learning engineer.
- Strong Python skills and a proven track record of writing production-quality code.
- Experience in building and evaluating models for tabular classification problems (preferably using gradient-boosted decision trees like LightGBM, XGBoost, or CatBoost).
- Experience building applications with LLM APIs (e.g., OpenAI, Anthropic), including structured extraction, prompt engineering, and orchestration frameworks like LangChain or LangGraph.
- Familiarity with document and unstructured data processing (PDF/image extraction, text parsing, or similar).
- Experience with ML lifecycle tooling for training orchestration, experimentation, and model monitoring (e.g., Kubeflow, Airflow, MLflow, or equivalent internal platforms).
- Proficient in using AI-powered developer tools (e.g., Claude Code, Cursor, or similar) to accelerate iteration, debugging, and code quality in daily development workflows.
- Mastery in transforming a simple problem or business scenario into a solution that interacts with multiple software components, and executing it by writing clear, easily understood, well-tested, and extensible code.
- Comfortable navigating a large codebase, debugging others' code, and providing feedback through code reviews.
- Demonstrated ownership of personal growth, proactively seeking feedback from your team, manager, and stakeholders.
- Strong verbal and written communication skills to support effective collaboration with a global engineering team.