Sr. Pharmacoepidemiologist

We are seeking a talented Pharmacoepidemiologist to join our team to support projects at the NIH’s National Center for Advancing Translational Sciences (NCATS). In this role, you will collaborate with clinical and data scientists, methodologists, and software engineers to develop and execute exemplar causal inference studies. You will work as a subject matter expert to create a real-world evidence (RWE) methods decision tree; support master protocol development; and support development of gold-standard guides and methodologies for conducting best practices causal inference research. You will: design, execute, and analyze studies using the National Clinical Cohort Collaborative (N3C) data; review and recommend strategies for selecting study designs to answer causal inference questions; help establish, and implement appropriate analytic value sets.

The ideal candidate for the Pharmacoepidemiologist position is a highly skilled professional with a Ph.D. in Pharmacoepidemiology, Epidemiology, Biostatistics, Causal Inference or related field. This person has experience with electronic health record and/or claims data and a strong understanding of observational study principles including: missing data handling methods; temporal research questions (cross-sectional, longitudinal); causal contrast of interest (e.g., intent-to-treat, per-protocol); effect measure of interest (e.g., risk ratio, hazard ratio); and estimands (e.g., average treatment effect, average treatment effect in the treated) of interest. Your research experience includes one or more of the following: target trial emulation, sequential trial analysis, marginal structural models, longitudinal matching, G methods, or equivalent causal inference methods, realized in multiple primary-author publications. Fluency with coding languages and tools is expected (i.e. SQL, Python, and R).

Responsibilities:

• Serve as SME for RWE causal inference studies.
• Design and execute studies with N3C EHR data considering the following: extent of missing data; missing data handling methods; temporal component of research studies (i.e. cross-sectional, longitudinal); the causal contrast of interest (e.g., intent-to-treat, per-protocol); the effect measure of interest (e.g., risk ratio, hazard ratio); and estimand (e.g., average treatment effect, average treatment effect in the treated) of interest.
• Develop and operationalize decision-support frameworks to standardize how causal inference studies are designed, executed, and evaluated across projects.
• Contribute to the development of reusable, platform-level components that support reproducible and scalable RWE generation.
• Review and recommend strategies for selecting individuals in clinical cohorts.
• Ensure the highest data quality and minimization of bias.
• Use tools and languages such as Python, R, SQL, and Spark.
• Help establish and implement appropriate analytic value sets.
• Collaboratively produce extensive documentation (i.e. through training material, research protocols, ope