Senior / Principal Data Scientist, EHR AI

The role

You will build models using longitudinal EHR and claims data to predict disease progression and treatment response. You will work with large-scale data including clinical notes, imaging, and genetic data to generate real-world evidence for drug development.

What you will do

• Build, train, and validate predictive models on longitudinal EHR and claims data
• Benchmark and adapt EHR foundation models for patient representation
• Define and validate computable phenotypes and cohorts using OMOP CDM and standard vocabularies
• Apply causal methods such as target trial emulation alongside predictive models
• Answer EHR and RWE questions from Business Development and R&D
• Write reproducible, reviewed code
• Work with Engineering and Product to turn prototypes into reusable tools
• Lead a modeling workstream end to end and mentor other scientists at the Principal level

Required qualifications

• PhD in computer science, biomedical informatics, statistics, epidemiology, or a related quantitative field
• 2+ years of industry or research experience building machine learning models on EHR data, including linked claims or other real-world data
• Strong Python and deep learning expertise
• Familiarity with data lakes and distributed compute for large clinical datasets
• High comfort with LLMs, including coding agents
• Working knowledge of how EHR and claims data are generated and structured
• Fluency with clinical vocabularies and common data models, including ICD-10, SNOMED CT, LOINC, RxNorm, ATC, and OMOP CDM
• Familiarity with common uses of EHR data and RWE in drug development
• Rigorous evaluation habits: temporal and site-held-out validation, calibration, handling of censoring, and prevention of label leakage
• Ability to explain technical results clearly to scientific and non-technical stakeholders

Nice to have

• Experience pretraining, fine-tuning, or rigorously benchmarking EHR foundation models or LLM-based approaches to patient timelines
• Causal inference on observational health data: target trial emulation, propensity score methods, instrumental variables, doubly robust or ML-based estimators
• Use of LLMs for clinical text, such as phenotyping or information extraction from clinical notes
• Experience with OHDSI tools and network studies, or with large linked EHR and biobank resources
• Experience in pharma, biotech, or health tech applying EHR models to drug development questions
• Exposure to health economics and outcomes research (HEOR)

Benefits

• Equity
• Comprehensive benefits
• Generous perks

Before you apply

• Please apply only if you reside in New York City, Boston metro areas, Research Triangle (NC), or San Francisco Bay Area or are willing to relocate

About the company

Formation Bio is a tech and AI driven pharma company that builds technology platforms to accelerate drug development and clinical trials. The company partners with, acquires, or in-licenses drugs to bring new medicines to patients.