Back to Job Listings

Principal Data Scientist, EHR AI

San Francisco

SpringCube

Full-time - Principal Engineer

Healthcare, Biotech, Pharma & Life Sciences

Posted 1 week ago

$200,000 - $250,000

Contact Employer
  • Share:
Send Feedback
Report This Job

Job Description

This job was selected by the SpringCube team to help AI, Data and Cloud Engineers discover relevant San Francisco Bay Area employers. Sign up to view the full employer details and apply directly with the hiring company.

Company Overview

The company is a technology-driven pharmaceutical organization focused on using artificial intelligence, data science, and technology platforms to improve drug development and clinical research. Its approach combines advanced computational capabilities with pharmaceutical development expertise to accelerate clinical trials and bring new treatments to patients more efficiently.

Responsibilities

  • Build, train, and validate predictive machine learning models using longitudinal EHR and claims data to assess disease progression, time-to-event outcomes, and patient-level treatment responses.
  • Benchmark and adapt EHR foundation models for patient representation, comparing their performance against established tabular and sequence-based modeling approaches.
  • Define and validate computable phenotypes and patient cohorts using the Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) and standardized clinical vocabularies.
  • Develop features from clinical notes and other unstructured healthcare data sources.
  • Apply causal inference methods, including target trial emulation, alongside predictive modeling to identify treatments that may modify disease progression.
  • Address EHR and real-world evidence questions supporting business development due diligence and research and development programs within short delivery timelines.
  • Communicate analytical findings with explicit consideration of uncertainty, potential bias, and limitations.
  • Develop reproducible, well-documented, and reviewed code.
  • Collaborate with Engineering and Product teams to transform research prototypes into reusable tools and production-ready capabilities.
  • Principal-Level Responsibilities: Lead modeling workstreams from initial problem definition through execution, establish technical direction, and mentor other data scientists.

Qualifications

Required Qualifications

  • PhD in Computer Science, Biomedical Informatics, Statistics, Epidemiology, or a related quantitative discipline.
  • 2+ years of industry or research experience developing machine learning models using EHR data, including linked claims or other real-world datasets.
  • Demonstrated research or industry results through peer-reviewed publications, deployed models, or externally validated model performance.
  • Strong Python programming skills and deep learning expertise.
  • Familiarity with data lakes and distributed computing environments for processing large-scale clinical datasets.
  • Strong familiarity with large language models (LLMs), including coding agents, as part of regular technical workflows.
  • Working knowledge of how EHR and claims data are generated and structured, including:
    • Patient encounters and diagnoses.
    • Medical procedures and medications.
    • Laboratory results and vital signs.
    • Clinical notes and documentation.
    • Insurance coverage periods and reimbursement records.
  • Understanding of clinical coding practices, missing data, and variations across healthcare systems, sites, payers, and countries.
  • Familiarity with clinical vocabularies and common data models, including:
    • ICD-10 and national modifications.
    • SNOMED CT.
    • LOINC.
    • RxNorm.
    • ATC.
    • Procedure coding systems.
    • OMOP Common Data Model (CDM).
  • Understanding of common applications of EHR data and real-world evidence in pharmaceutical development, including:
    • Clinical phenotyping and patient cohort definition.
    • Clinical trial feasibility and eligibility.
    • Disease natural history analysis.
    • Outcome prediction.
    • External control arms.
    • Comparative effectiveness research.
    • Safety signal detection.
  • Strong model evaluation practices, including temporal and site-held-out validation, calibration, appropriate handling of censoring, and prevention of label leakage.
  • Ability to communicate technical findings clearly to scientific and non-technical stakeholders.

Disclaimer

SpringCube curates tech job listings from various company websites to support tech professionals globally.

  1. No Endorsement: Job ads on SpringCube do not imply endorsement of their authenticity or quality.
  2. No Client Relationship: This company is not a client of SpringCube unless stated.
  3. To Apply: Click the “Apply” button to be redirected to the hiring company’s application page for this job.
  4. No Liability: SpringCube is not liable for inaccuracies.
‹