Work with vast national datasets of medical and pharmacy claims data to interpret, analyze, and build datasets that deliver actionable insights to Trella’s proprietary solutions.
Design, build, and maintain scalable Databricks workflows and jobs for processing healthcare claims data.
Develop and optimize PySpark and SQL pipelines for performance, reliability, and efficiency.
Implement data quality monitoring and validation frameworks to ensure completeness, accuracy, and consistency of claims data.
Support modernization by refactoring legacy SAS scripts into Databricks.
Act as a subject matter expert on healthcare data sources, calculations, and methodologies.
Collaborate with the product team to size and scope new analytic projects, defining specifications and requirements.
Continuously enhance your knowledge of the healthcare industry through independent research and professional development.

5+ years of experience in data science, preferably within healthcare space.
Advanced SQL and Python skills (e.g. writing complex data processing scripts and automating workflows).
Experience working with Databricks, including Spark SQL and PySpark for analytics, data modeling, and machine learning workflows.
A deep understanding of data lineage to track and visualize data dependencies, identifying upstream/downstream impacts.
Experience with statistical modeling including regression, imputation techniques, and risk scoring.
Strong knowledge of medical claims data (e.g., Medicare, Medicaid, Commercial) as well as medical coding systems (ICD10, CPT, HCPCS, MS DRG, NPPES NPI).
Excellent problem-solving, time management, and communication skills.
Familiarity with software development tools like Jira, Confluence, and Bitbucket.
A passion for using data to improve healthcare and a love for solving complex problems.
Bachelor's or Master’s degree in a technical field or equivalent experience.

Senior Data Scientist

Key skills