Formation Bio
Associate Director/Director, Data Science, EHR AI
$214K–$307K
Boston, MA +3 · Director · Full-time · Posted Apr 30, 2026
- Location
- Boston, MA
New York, NY
116 Huntington Ave., Back Bay, Boston, MA, 02116
16 E 34th St., New York City, NY, 10016 - Experience
- 5+ years of industry or research experience building ML models on EHR data; 2+ years of people management.
- Education
- PhD in computer science, biomedical informatics, statistics, epidemiology, or a related quantitative field.
About the job
Leads the EHR AI team, building and validating models that convert longitudinal health data into evidence for drug selection, indication strategy, and clinical trial design.
What you'll do
- Set technical strategy, build and lead the team, and deliver against portfolio priorities.
- Develop predictive and causal analyses using EHR and claims data; evaluate EHR foundation models.
- Deliver RWE analyses for diligence and R&D, and partner with Engineering, Product, and data partners to operationalize results.
What they ask for
- PhD in computer science, biomedical informatics, statistics, epidemiology, or a related quantitative field.
- 5+ years building machine learning models on EHR data, including linked claims or other real-world data, with substantiated results.
- 2+ years managing data scientists or ML researchers as direct reports.
- Hands-on proficiency in Python and modern ML frameworks; high comfort with LLMs; working knowledge of EHR/claims data, clinical vocabularies, and RWE applications.
Nice to have
- Experience with EHR foundation models or LLM-based patient timelines; causal inference on observational health data.
- Experience with OHDSI tools, large linked EHR and biobank resources, or EHR models influencing drug or trial decisions.
Pay
$213,500 - $267,000 (total pay; Associate Director); $245,500 - $307,000 (total pay; Director)
Tools
Python, ICD-10, SNOMED CT, LOINC, RxNorm, ATC, OMOP CDM, LLMs
AI focus
Leads machine learning and AI for EHR and real-world data, including EHR foundation model evaluation and adaptation, patient representation, prediction, and causal analysis for drug development.
Model-written summary · the original posting is authoritative