AI Actuarial Modeling Developer

Quilvex Systems

Remote · $130k – $160k / year · Contract · Posted 4 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

Traditional actuarial models are built in R or Excel by people who learned their craft when GLMs were cutting edge. The insurance industry is starting to incorporate ML — gradient boosting, neural networks, causal models — but doing it in ways that satisfy regulators and stay interpretable enough for pricing committees is genuinely hard. We're building the ML layer on top of a traditional actuarial platform used by 15 specialty insurers. The challenge is hybrid modeling: combining actuarial domain knowledge with modern ML techniques in ways that improve predictions without sacrificing the interpretability actuaries need to explain decisions to regulators. This is a 10-month contract for someone who understands both worlds: strong ML engineering skills and enough actuarial knowledge to have an informed conversation with a credentialed actuary. Prior P&C insurance experience is strongly preferred.

Responsibilities

Build hybrid models combining actuarial methods with ML for loss reserving and pricing
Implement gradient boosting and GLM models for personal and commercial lines pricing
Create model explainability tools meeting regulatory documentation requirements
Validate ML models against actuarial benchmarks and industry standards
Collaborate with credentialed actuaries to encode domain assumptions into models
Deliver model documentation suitable for state insurance department review

Requirements

5+ years in ML engineering with insurance or financial services experience
Familiarity with actuarial concepts: loss triangles, chain-ladder, IBNR estimation
Strong Python and R skills for statistical modeling
Experience with model explainability frameworks like SHAP or LIME
Prior P&C insurance actuarial modeling experience strongly preferred