Associate Director/Director, Data Science, EHR AI

About the Position

As the Associate Director or Director leading the EHR AI team within Data Science at Formation Bio, you will build and lead our capability for learning from real-world data (RWD): electronic health records (EHR) together with claims and other real-world sources. Your models will turn longitudinal patient data into real-world evidence (RWE) that shapes which drugs we acquire, which indications we pursue, and how we design trials. You will set the technical direction for machine learning on EHR and other real-world data, including the evaluation and adaptation of EHR foundation models, and apply it to the questions that move our portfolio: which approved drugs alter the course of disease, which patients progress and when, and how a trial population is likely to respond. You will work with large-scale, longitudinal EHR data from health systems, linked to claims, clinical notes, and imaging, alongside biobank-scale genetic and molecular data.

You will report to the VP of Data Science and partner primarily with Business Development and R&D; on the technology side, you will work closely with Engineering and Product. This role owns the modeling, the scientific standards, and the translation of results into decisions. The ideal candidate has built and validated models on EHR and claims data, knows the data well enough to anticipate where it misleads, and can explain what a model means for a deal or a trial to executives and clinicians.

Responsibilities

Lead the EHR AI team within Data Science: set technical strategy, hire and develop the team, and own delivery against portfolio priorities

Build and validate predictive models on longitudinal EHR and claims data (disease progression, time-to-event outcomes, patient-level treatment response) with evaluation designs that hold up under temporal and cross-site shift

Evaluate, adapt, and fine-tune EHR foundation models for patient representation, and determine where they outperform simpler baselines

Combine predictive modeling with causal approaches such as target trial emulation to identify approved drugs that modify disease course, generating repurposing and indication expansion candidates

Deliver fast, rigorous EHR and RWE analyses for Business Development diligence and R&D programs: cohort definition and feasibility, natural history, patient segmentation, and endpoint and trial design support

Partner with Engineering and Product to turn prototypes into reusable, self-serve capabilities, and with data partners on dataset selection and fitness for use

Set standards for phenotype definition, validation, and reproducibility across all EHR and RWD work

About You

Required Qualifications

PhD in computer science, biomedical informatics, statistics, epidemiology, or a related quantitative field (required)

5+ years of industry or research experience building machine learning models on EHR data, including linked claims or other real-world data, with substantiated results: peer-reviewed publications, deployed models, or externally validated performance

2+ years of people management, leading data scientists or ML researchers as direct reports

Working knowledge of how EHR and claims data are generated and structured: encounters, diagnoses, procedures, medications, labs, vitals, clinical notes, coverage periods, and reimbursement records, along with coding practices, missingness, and variation across sites, payers, and countries

Fluency with clinical vocabularies and common data models, including ICD-10 and its national modifications, SNOMED CT, LOINC, RxNorm, ATC, procedure coding systems, and the OMOP CDM

Familiarity with common uses of EHR data and RWE in drug development: phenotyping and cohort definition, trial feasibility and eligibility, natural history, outcome prediction, external control arms, comparative effectiveness, and safety signal detection

Hands-on proficiency in Python and modern ML frameworks; you can review code and run experiments yourself

High comfort with LLMs, including coding agents, as part of your daily work

Strong communication skills with clinical, scientific, and executive audiences

Preferred Qualifications

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 (e.g., All of Us, UK Biobank)

Track record of EHR models that influenced acquisition, licensing, trial design, or regulatory decisions

Exposure to health economics and outcomes research (HEOR)

Total Compensation Range: Associate Director $213,500 - $267,000; Director $245,500 - $307,000