AI Catastrophe Loss Estimation Developer

Quilvex Systems

Hybrid · $200k+ / year · Full-time · 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

Catastrophe loss estimation is the actuarial foundation of reinsurance pricing, portfolio accumulation management, and regulatory capital adequacy. When a hurricane makes landfall or an earthquake strikes an urban area, the question the industry asks within hours is: what is our expected total insured loss? The models that answer that question — catastrophe models combining atmospheric science, engineering vulnerability curves, and exposure data — are among the highest-stakes ML systems in the financial industry. Our insurance analytics platform serves 8 reinsurance companies and 15 primary insurers. Catastrophe loss estimation is the most technically demanding capability we offer. Current cat models rely on vendor-supplied event sets and vulnerability functions that don't reflect recent climate shifts or the exposure composition of specific client portfolios. We're building proprietary ML-enhanced cat models that improve on vendor models for our clients' specific exposure mixes. This is a principal-level role requiring deep actuarial science and ML expertise. You'll lead cat model development: building ML-enhanced vulnerability functions from historical loss data, implementing climate-adjusted event set generation, and developing the real-time accumulation monitoring that tells underwriters when a storm system approaching landfall could breach portfolio concentration limits. The role is hybrid — 2 days per week in NYC.

Responsibilities

Build ML-enhanced vulnerability functions from historical loss data improving on vendor standard curves for specific exposure types
Implement climate-adjusted event set generation incorporating updated Atlantic basin and wildfire hazard projections
Develop real-time accumulation monitoring alerting underwriters when approaching storm systems threaten concentration limits
Create exceedance probability curve construction for portfolio return period loss estimation
Build secondary peril correlation models capturing demand surge, fire following earthquake, and storm surge interactions
Validate ML model outputs against independent vendor model benchmarks and historical event realizations

Requirements

8+ years in catastrophe modeling, actuarial science, or climate risk ML with reinsurance exposure
Deep expertise in natural hazard science, vulnerability modeling, and insurance loss estimation
Strong Python and Spark skills with large-scale geospatial and exposure data processing
Understanding of reinsurance program structures, accumulation management, and cat model regulatory requirements
Track record building proprietary cat models adopted by reinsurance clients for pricing and capital decisions