Sr. Data Scientist, Outcomes Research

Tempus AI · Vertical AI · IL · Remote

This role focuses on outcomes research within the healthcare domain, utilizing real-world evidence (RWE) and health economics and outcomes research (HEOR) methodologies. The primary responsibilities involve leading and executing projects related to outcomes analysis, treatment patterns, and healthcare resource utilization, often involving large-scale healthcare datasets like claims and EHRs. While the company uses AI, this specific role is centered on data analysis, epidemiological studies, and methodological guidance rather than core AI/ML model development or deployment.

What you'd actually do

  1. Lead and execute HEOR and RWE projects (e.g., outcomes analysis, treatment patterns, and healthcare resource utilization) with external Pharma, academic, and other partners.
  2. Represent the Outcomes Research function and collaborate with internal and external stakeholders in the design, analysis, interpretation, and publication of real-world studies.
  3. Work on complex problems, exercising judgment in selecting and adapting appropriate epidemiologic and health economic methodologies.
  4. Work with interdisciplinary groups of scientists, engineers, and product developers to translate research into clinically actionable insights for our clients
  5. Stay current with the latest methodological advances in real world studies

Skills

Required

  • R
  • SQL
  • large-scale healthcare datasets
  • observational data analysis
  • HEOR methodologies
  • RWE methodologies
  • confounding techniques (e.g., propensity score matching, inverse probability weighting)
  • claims data analysis
  • EHR data analysis
  • clinico-genomic databases analysis
  • time-to-event analysis
  • survival methodology

Nice to have

  • version control
  • software testing
  • oncology clinical trials analysis
  • regulatory submissions to the FDA
  • model building and validation support
  • client facing experience
  • consulting experience

What the JD emphasized

  • extensive experience and interest in design and analysis of pharmacoepidemiological studies
  • Computational skills using R and SQL, specifically applied to large-scale healthcare datasets.
  • Strong data manipulation and analysis skills tailored to observational data.
  • Deep familiarity with HEOR and RWE methodologies, including techniques to address confounding (e.g., propensity score matching, inverse probability weighting).
  • Experience analyzing large, complex real-world datasets, including administrative claims, electronic health records (EHR), and clinico-genomic databases.
  • Hands-on experience in helping to prepare regulatory submissions to the FDA