Description

Build statistical models and machine learning algorithms to drive insights into risk modeling, pricing, and claims analysis. You will own the end-to-end data lifecycle, from ETL and feature engineering to model deployment and stakeholder communication.

This role is hybrid.

Responsibilities

• Develop regression, classification, clustering, and time series forecasting models for the reinsurance domain.
• Build and manage ETL processes, data wrangling, and feature engineering workflows using Spark and Hadoop.
• Deploy models and data pipelines on Azure or AWS cloud platforms.
• Communicate complex technical findings and data storytelling to non-technical stakeholders.
• Collaborate with actuarial, underwriting, and IT teams to apply statistical modeling to risk assessment.

Required Skills

• 5+ years of experience in data science or machine learning roles.
• Proficiency in Python with expertise in Pandas, NumPy, and Scikit-learn.
• Strong SQL skills for data manipulation and extraction.
• Experience with Spark and Hadoop for big data processing.
• Hands-on experience with ETL processes and data engineering.
• Working knowledge of Azure or AWS for model deployment and pipelines.
• Competency in data visualization using Power BI.
• Ability to apply statistical modeling to risk assessment and claims analytics.

Preferred Skills

• Experience with NLP, Monte Carlo simulations, or stochastic modeling.
• Familiarity with Git, CI/CD pipelines, or geospatial mapping tools.
• Knowledge of R, SAS, or regulatory frameworks like Solvency II and IFRS 17.

Key Skills

Education

Any Gradute