AI Pull Request Risk Scoring Engineer

Inovex Intelligence

Remote · $160k – $200k / year · Full-time · Posted 2 months ago

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

This role is no longer accepting applications

Don't miss the next role like this

Create a free profile with your skills. We match you to new AI roles as they open, and companies hiring can contact you directly.

Create free profile, 2 minutes

Similar open roles you can apply to now:

See all open AI jobs

About the role

We just closed our Series B and engineering teams using our platform are shipping faster than ever — which means riskier pull requests are slipping through review more often too. We need a senior engineer to build a risk scoring model that flags PRs likely to cause incidents based on code churn, historical blame patterns, test coverage, and reviewer signals. The model runs inline in CI, deployed on our Kubernetes cluster, and needs to be fast enough that developers never notice the extra step. Get this right and you directly reduce the incident rate for every team on our platform.

Fully remote.

Responsibilities

Design and train the PR risk scoring model using historical code and incident data
Deploy the scoring service on Kubernetes with sub-second inline CI latency
Continuously validate model precision against real post-merge incident outcomes
Work with the platform team to integrate risk scores into the review UI

Requirements

Strong scikit-learn experience for building and validating classification models
Production experience deploying low-latency services on Kubernetes and Docker
Comfortable working with noisy, imperfect labels like post-merge incident data
Experience with developer tooling or CI/CD systems a strong plus