Data Scientist (100% REMOTE ROLE)- P&C Domain Experience

Role & Responsibilities Overview:

• Develop machine learning models for various P&C insurance products elated to pricing, customer behavior, retention, price sensitivity, risk segmentation etc.
• Build, enhance, and maintain GLM-based pricing models (frequency, severity, pure premium) for insurance products
• Perform model comparison and benchmarking between traditional actuarial models and ML approaches
• Design and implement feature engineering pipelines using policy, claims, exposure, and behavioral data
• Conduct model validation, performance monitoring, and stability analysis over time
• Deploy and operationalize models using Databricks-based workflows
• Partner with actuarial, underwriting, and product teams to translate business problems into analytical solutions
• Document modeling methodology, assumptions, and results to support model governance and regulatory review

Candidate Profile:

• Location - Based out of US, (Cincinnati, Ohio Preferred)
• 7+ years of experience in P&C insurance analytics, pricing, or actuarial-adjacent Data Science roles with proficiency in advanced Machine Learning, NLP, DL techniques
• Hands-on, end-to-end ownership mindset from data preparation to model deployment
• Proven ability to work with large, complex insurance datasets with the ability to explain analytical results to non-technical stakeholders
• Strong understanding of P&C insurance pricing concepts, customer life cycle, rating variables, and risk segmentation
• Bachelors or Master's degree in data science, economics, mathematics, computer science/engineering, operations research or related analytics areas

Technical skills:

• Machine Learning algorithms for tabular data (Gradient Boosting, Random Forests, XGBoost, LightGBM, NLP-Unstructured)
• GLM modeling expertise (Poisson, Gamma, Tweedie, Logistic)
• Python for data analysis and modeling (pandas, numpy, scikit-learn, statsmodels)
• Databricks / Spark (PySpark) for large-scale data transformation and feature engineering
• SQL for data extraction, transformation, and analytical queries
• Model explainability techniques (e.g., SHAP, partial dependence)
• Experience with model deployment, scoring pipelines, and performance monitoring