Remote Underwriting ML Engineer II — Real-Time Risk

Affirm, Inc.; Northern (KY); Hybrid; USD 146,000 - 206,000; Full time

Benefits offered by this job

Health, dental and vision coverage

Stipends for health, wellness and tech

Employee stock purchase plan (ESPP)

Job summary

Affirm, Inc. is seeking an Underwriting ML Engineer to build real‑time decisioning systems that assess repayment risk. You will develop models, implement scalable feature pipelines, and productionize models within batch or streaming contexts, while monitoring performance and reliability.

You will collaborate across Engineering, Risk Analytics, Product, and ML Platform, have 2+ years of experience or a PhD, and bring strong Python, PyTorch, and distributed processing skills to the team.

Qualifications

• 2+ years in machine learning engineering or a related PhD.
• Strong Python skills and production-grade coding experience.
• Experience building and evaluating classification models (GBDTs, etc.).
• Familiar with PyTorch and distributed data processing (Spark).
• Experience with ML lifecycle tooling (Kubeflow, Airflow, MLflow).
• Ability to write clear, well-tested, extensible code and operate within large codebases.

Responsibilities

• Develop and iterate underwriting prediction models for tabular and sequential data.
• Build scalable feature pipelines and training datasets from private and third‑party signals.
• Prototype ideas, run offline experiments, and productionize top approaches with risk controls.
• Productionize models in batch and real-time decision systems, improving reliability and latency.
• Instrument model and data health, and define retraining/backtesting workflows.
• Collaborate with Engineering, Risk Analytics, Product, and ML Platform to communicate results clearly.

Skills

Python

Production-grade code

ML modeling

GBDT models

PyTorch

Spark

Kubeflow / MLflow

Code reviews

Debugging large codebase

Education

Bachelor's degree

Equivalent practical experience

Tools

LightGBM

XGBoost

CatBoost

PyTorch

Spark

Kubeflow / Airflow

MLflow

Job description

Affirm, Inc. is seeking an Underwriting ML Engineer to build real‑time decisioning systems that assess repayment risk. You will develop models, implement scalable feature pipelines, and productionize models within batch or streaming contexts, while monitoring performance and reliability.

You will collaborate across Engineering, Risk Analytics, Product, and ML Platform, have 2+ years of experience or a PhD, and bring strong Python, PyTorch, and distributed processing skills to the team.