ML Engineer II — AI for Disputes & Refunds (Remote)

Latitude; Las Vegas, Northern (NV, KY); Hybrid; USD 146,000 - 206,000; Full time

Benefits offered by this job

100% subsidized medical coverage for你u

Job summary

Affirm is seeking a machine learning engineer to build AI systems that automate dispute, chargeback handling, and refunds, with structured outputs from unstructured data. You will prototype models, run offline experiments, and deploy best approaches to production with risk controls.

You will collaborate across Engineering, Servicing Operations, Product, and ML Platform to define requirements and communicate results clearly to both technical and non-technical audiences.

Qualifications

• 2+ years of experience as a machine learning engineer.
• Strong Python skills and production-quality code.
• Experience building and evaluating models for tabular classification (LightGBM/XGBoost/CatBoost).
• Experience with LLM APIs (OpenAI, Anthropic) including structured extraction and prompt engineering.
• Familiarity with document/unstructured data processing (PDF/image extraction).
• Experience with ML lifecycle tooling (Kubeflow, Airflow, MLflow).
• Proficient with AI-powered developer tools (Claude Code, Cursor).
• Ability to write clear, well-tested, extensible code and navigate large codebases.
• Strong communication and collaboration skills.
• Bachelor's degree or equivalent practical experience.

Responsibilities

• Develop AI systems that automate dispute and chargeback handling with structured outputs.
• Build models to automate refunds and speed up customer recoveries.
• Create and maintain evidence extraction pipelines using LLM-powered workflows.
• Prototype new modeling ideas, run offline experiments, and push best approaches to production with risk controls.
• Collaborate with Engineering, Servicing Operations, Product, and ML Platform to define requirements and communicate results.

Skills

Python

Production code

Tabular models

LightGBM/XGBoost/CatBoost

LLM APIs

LangChain/ LangGraph

Unstructured data processing

ML lifecycle tooling

AI developer tools

Code reviews

Communication

Bachelor's degree or equivalent

Education

Bachelor's degree or equivalent

Tools

LightGBM

XGBoost

CatBoost

LangChain

LangGraph

Kubeflow

Airflow

MLflow

Job description

Affirm is seeking a machine learning engineer to build AI systems that automate dispute, chargeback handling, and refunds, with structured outputs from unstructured data. You will prototype models, run offline experiments, and deploy best approaches to production with risk controls.

You will collaborate across Engineering, Servicing Operations, Product, and ML Platform to define requirements and communicate results clearly to both technical and non-technical audiences.