AI Underwriting Risk Explainability Engineer

Maltex AI

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

PyTorch, MLflow, and a decade of underwriting data are the core of what we build. Our risk models decide pricing for thousands of commercial policies every week, and regulators increasingly demand that every score come with a clear, auditable explanation. You'll design the explainability layer that sits on top of our production risk models, translating feature attributions into language underwriters and auditors can actually act on. This isn't a bolt-on reporting tool — it becomes part of the decision path itself, gating any score that can't be explained with confidence. If you'd rather ship something regulators trust than chase another leaderboard metric, this role is built for you.

Responsibilities

Own the full explainability pipeline from model output to underwriter-facing report
Partner with product to define what counts as an acceptable explanation for a denied claim
Build regression tests that catch explanation drift when models are retrained
Work directly with compliance to keep audit trails defensible under regulatory review

Requirements

Production experience with PyTorch and MLflow model lifecycle tooling
Comfort reading and explaining gradient-based and SHAP-style attribution methods
Experience shipping ML systems in a regulated industry (insurance, banking, healthcare)
Working knowledge of Docker-based deployment on AWS