Data Scientist

Our client is seeking a Data Scientist to support the Group Insurance organization, with a focus on traditional machine learning use cases for medical and financial underwriting. This role is hands-on and data-driven, partnering closely with actuaries and technology teams to develop and support predictive models used in underwriting and pricing.

Responsibilities

• Develop and apply traditional machine learning models (classification, survival models) for underwriting and pricing use cases

• Perform data extraction, cleaning, validation, and feature engineering on large datasets

• Analyze data quality issues and assemble usable analytical datasets from multiple sources

• Build and evaluate models using Python in an AWS cloud environment

• Partner with actuaries, IT, and ML engineering teams to support model deployment and testing

• Assist with troubleshooting, validation support, and research for failed test cases

3+ years of experience in data science, applied statistics, or machine learning

• Strong proficiency in Python (NumPy, Pandas, scikit-learn, seaborn)

• Solid SQL skills for working with large databases

• Strong understanding of statistical and machine learning principles

• Experience building classification models; survival modeling experience strongly preferred

• Ability to communicate effectively with non-data science stakeholders

• Master's degree (PhD a plus; Bachelor's considered with strong relevant experience) - Experience working in AWS (e.g., S3, SageMaker notebooks)

• Exposure to insurance, underwriting, actuarial, or risk modeling domains

• Familiarity with software deployment or DevOps concepts (nice to have, not required)