Underwriting ML Engineer II — Real-Time Risk (Remote)

Affirm; Portland (OR); On-site; USD 146,000 - 206,000; Full time

Benefits offered by this job

Health coverage for you and dependents

Flexible Spending Wallets

Time off

ESPP

Job summary

Affirm is reinventing credit to make it more honest and friendly, giving consumers the flexibility to buy now and pay later without hidden fees or compounding interest. On the Underwriting ML team, you’ll build and improve machine learning systems that make real-time transaction decisions, assessing repayment risk and expected value of every Affirm checkout.

You’ll work closely with ML engineers, data, and platform teams to take models from idea to prototype to production, and to keep them

Qualifications

• 2+ years of ML engineering experience or a PhD in a relevant field.
• Strong Python skills and production-quality code.
• Experience building/evaluating models for classification (GBDTs) like LightGBM/XGBoost/CatBoost.
• Experience with PyTorch and distributed data processing (Spark).
• Experience with ML lifecycle tooling (Kubeflow, Airflow, MLflow).
• Proficient using AI-powered developer tools to accelerate iteration and quality.

Responsibilities

• Develop and iterate on underwriting prediction models.
• Build and scale feature pipelines and datasets from signals.
• Prototype new modeling ideas, run offline experiments, push best approaches to production.
• Productionize models in batch and/or real-time decision systems.
• Instrument and monitor model and data health; define retraining workflows.
• Collaborate with Engineering, Risk Analytics, Product, and ML Platform.

Skills

Python

Production code

GBDT models

PyTorch

Spark

MLflow

Code reviews

Communication

Education

Bachelor’s degree or equivalent

Tools

Kubeflow

MLflow

Airflow

Ray

Job description

Affirm is reinventing credit to make it more honest and friendly, giving consumers the flexibility to buy now and pay later without hidden fees or compounding interest. On the Underwriting ML team, you’ll build and improve machine learning systems that make real-time transaction decisions, assessing repayment risk and expected value of every Affirm checkout.

You’ll work closely with ML engineers, data, and platform teams to take models from idea to prototype to production, and to keep them