Senior Data Scientist

Responsibilities

• Model and transform raw EHR and claims data into clean, canonical, and analytics-ready datasets using SQL, Python, and clinical standards like OMOP
• Build and manage scalable data pipelines using Dagster, dbt, and Snowflake
• Conduct hands-on RWD analyses to answer scientific and strategic research questions regarding disease epidemiology and treatment patterns
• Partner with Data Scientists and clinical leads to design and execute observational studies
• Implement data validation, completeness, and observability frameworks
• Apply Generative AI techniques to accelerate data structuring and insight generation
• Communicate findings clearly to technical and non-technical stakeholders

Requirements

• 5+ years of experience, with at least 2 years in healthcare or life sciences
• Direct exposure to EHR or claims datasets
• Experience with biomedical schemas such as UMLS, LOINC, ICD9/10, or MeSH
• Fluency in SQL and Python
• Experience building longitudinal patient cohorts from EHR or claims data
• Understanding of causal inference frameworks like potential outcomes and target trial emulation
• Familiarity with RWD study design concepts and modern data infrastructure (Snowflake, dbt, Dagster)

Preferred Qualifications

• Experience in regulated or privacy-sensitive data environments (PHI)
• Experience working with commercial RWD vendors like Truveta, Optum, Komodo, or IQVIA

About the Company

Formation Bio is a tech and AI driven pharma company differentiated by radically more efficient drug development. The company builds technology platforms and capabilities to accelerate all aspects of drug development and clinical trials to bring new medicines to patients faster.