Underwriting ML Engineer II — Real-Time Risk & Models

Affirm; Las Vegas (NV); On-site; USD 146,000 - 225,000; Full time

Benefits offered by this job

Health coverage

Spending stipends

Flexible time off

Employee stock purchase plan

Job summary

Affirm seeks an experienced ML Engineer on the Underwriting ML team to build real-time decisioning systems for checkout risk and value assessment. You’ll collaborate with data, engineering and product teams to move ideas into prototype and production, with robust monitoring and measurement to adapt to changing conditions.

The role emphasizes Python, PyTorch, and scalable feature pipelines, with a focus on production-quality code and clear communication across stakeholders.

Qualifications

• 2+ years of experience as a machine learning engineer or a PhD in a relevant field.
• Strong Python skills and production-quality code experience.
• Experience with ML models for classification (GBDT/LightGBM/XGBoost/CatBoost).
• Experience with PyTorch and distributed data processing frameworks (Spark).
• Familiar with ML lifecycle tooling (Kubeflow/Airflow/MLflow).

Responsibilities

• Develop and iterate on underwriting prediction models for tabular and sequential data.
• Build and scale feature pipelines and training datasets from multiple signals.
• Prototype modeling ideas, run offline experiments, and push best approaches to production with risk controls.
• Productionize models to integrate into batch or real-time decision systems with reliability and latency focus.
• Instrument and monitor model and data health; define retraining and backtesting workflows.
• Collaborate with Engineering, Risk Analytics, Product, and ML Platform to define requirements and communicate results.

Skills

Python

Machine Learning

PyTorch

LightGBM

Spark

Code quality

Education

Bachelor's degree in related field

Tools

Kubeflow

Airflow

MLflow

SQL

Job description

Affirm seeks an experienced ML Engineer on the Underwriting ML team to build real-time decisioning systems for checkout risk and value assessment. You’ll collaborate with data, engineering and product teams to move ideas into prototype and production, with robust monitoring and measurement to adapt to changing conditions.

The role emphasizes Python, PyTorch, and scalable feature pipelines, with a focus on production-quality code and clear communication across stakeholders.