Shepherd
Actuarial Data Science Lead
$200K–$240K
New York City +2 · On-site · Full-time · Posted Sep 25, 2026
- Location
- New York City
San Francisco
Chicago - Experience
- 7+ years of professional experience building and deploying personal auto or commercial lines predictive pricing models in production; experience managing a small team or project is also requested.
About the job
Own and deploy commercial auto pricing and loss-cost models, turning insurance and third-party data into pricing decisions and monitoring model performance.
What you'll do
- Develop, deploy, and iterate on pricing models and feature pipelines for Shepherd’s commercial auto book.
- Collaborate with actuaries and underwriters to develop features and validate model outputs; run experiments and back-tests.
- Monitor model drift, performance, and calibration, and communicate findings to stakeholders.
What they ask for
- 7+ years building and deploying personal auto or commercial lines predictive pricing models in production.
- ACAS/FCAS actuarial designation and familiarity with actuarial concepts such as loss development, exposure rating, and credibility.
- Strong statistical foundation, including GLMs, GBDTs, time series analysis, heavy tail distributions, and Bayesian methods.
- Proficiency in Python and SQL; experience with feature engineering on messy, real-world, small data.
Nice to have
- Experience in insurance, insurtech, fintech, or other regulated industries; exposure to telematics pricing models.
- Experience with NLP/document extraction from unstructured insurance submissions or model deployment infrastructure (AWS).
Pay
$200K – $240K (base salary)
Tools
Python, SQL, GLMs, GBDTs, AWS
AI focus
Use LLMs and AI tools to accelerate work; the role builds predictive pricing models and model monitoring, with NLP/document extraction from insurance submissions listed as a nice-to-have.
Model-written summary · the original posting is authoritative