Machine Learning Engineer

We are looking for a Machine Learning Engineer to own underwriting models at Grid, a Seattle fintech making 40, 000 to 50, 000 live credit decisions a month on a one to two second latency budget. You will read a user's bank transaction history, score the risk in their behavior, and ship the model that makes the call. Volume is growing fast as Grid scales ad spend, and the team is small enough that one person owns a model from ETL through deployment and monitoring.

What will you be doing?

Train and deploy underwriting models that score risk from bank transaction and user behavior data

Own the full path: ETL, feature engineering, training, deployment, monitoring, and the next iteration

Ship live inference that returns a decision inside one to two seconds at growing volume

Work on fraud detection, risk underwriting, and predictive analytics for payouts and repayments

Help set the standard for ML practice at Grid as the team grows

Key Requirements

Models you trained and put into production yourself, not models you consulted on

Experience with large-scale transaction or behavioral data

At least one full-time role at a startup or small team

Python and SQL, with a real training stack (XGBoost, PyTorch, or TensorFlow)

Fintech underwriting, lending, or fraud experience is a strong plus, not a requirement

On-site in Seattle five days a week