Senior Data Scientist (Casualty Insurance Claims)

About the role

We are seeking a Senior Data Scientist to architect and lead the development of our core Claim Clustering Platform. This role involves designing systems that move beyond experimentation into robust, production-grade solutions. You will collaborate with Machine Learning Engineers and MLOps specialists to ensure scalability, reliability, and continuous improvement. Additionally, you will serve as a critical bridge to Data and Application Engineering teams, ensuring seamless integration with downstream systems such as benchmarking and fraud detection.

Responsibilities

• Design and own the mathematical and technical framework for a scalable clustering engine that groups claims based on clinical, legal, and financial attributes.
• Partner with Machine Learning Engineers to translate prototypes into optimized production systems, and work with MLOps to implement automated retraining, monitoring, and model lifecycle management.
• Collaborate with Data and Application Engineering teams to define APIs and data contracts that power internal tools such as attorney and physician benchmarking, as well as fraud detection systems.
• Develop advanced representations of claims using both structured data (e.g., ICD codes, geographic data, indemnity and legal costs) and unstructured data (e.g., adjuster notes, medical records, legal documents).
• Act as a subject matter expert within the broader engineering organization, ensuring alignment between data science initiatives, system architecture, and production reliability standards.

Requirements

• 4-7 years in Data Science with a strong track record of deploying models into production environments.
• Deep experience with casualty claims, including at least 4 years of hands-on work in Workers’ Compensation and/or General Liability. Additional experience with auto is a plus.
• Familiarity with claim lifecycles, medical billing (ICD/CPT), litigation processes, and reserve dynamics is crucial.
• Strong proficiency in Python and solid software engineering fundamentals, including system design, CI/CD pipelines, and API development/versioning.
• Expertise in unsupervised learning techniques (clustering, dimensionality reduction) and NLP methods (transformers, embeddings, LLM-based approaches) for analyzing complex, unstructured data.
• Proven ability to lead and execute projects across Data Science, Engineering, DevOps, and Product teams.

Qualifications

• Bachelor's degree in Computer Science, Statistics, Mathematics, or a related field.
• Experience with big data technologies (Hadoop, Spark, etc.) is a plus.
• Experience with cloud platforms (AWS, Azure, Google Cloud) is a plus.

Skills

• Python programming skills.
• Experience with machine learning libraries (TensorFlow, PyTorch, Scikit-Learn).
• Knowledge of statistical analysis and data modeling.
• Experience with NLP and deep learning frameworks.
• Experience with data warehousing and ETL processes.

Benefits

• Competitive compensation and generous benefits package, including 401k company match!
• Full remote and flex/unlimited PTO.
• The opportunity to be part of a passionate team.

Pay

Compensation is competitive and commensurate with experience.

Schedule

This position offers a flexible schedule with full remote work options.