CV

Associate Statistical Project Leader

Sanofi

• Designed randomization strategy and post-analysis for a multi-regional, multi-period crossover trial and long-term extension, applying stratified CMH analysis and sensitivity analyses to support FDA and EMA submissions for a $2B+ drug program.
• Built reusable causal machine learning infrastructure in R Shiny, with methodology documentation adopted by hundreds of team members.
• Partnered with domain scientists and data programmers to define causal estimands, establish identification strategies, and deploy end-to-end pipelines that reduced reporting cycle time by approximately 25%.

Study Statistician

Sanofi

• Built a production-scale causal ML pipeline in Python for propensity score matching, covariate balance diagnostics, sensitivity analysis, and automated ATE reporting across a one-million-patient observational cohort.
• Estimated CATE across North American subgroups using generalized random forests with honest splitting and Bayesian shrinkage; presented the identification strategy and findings to FDA and EMA.
• Conducted random-effects meta-analysis across more than 100 studies and applied hierarchical Bayesian shrinkage to improve counterfactual placebo baseline estimates.
• Evaluated synthetic difference-in-differences and generalized random forests for production subgroup-discovery pipelines and authored methodology proposals adopted team-wide.

Graduate Research Assistant

George Mason University

• Developed methods for regression under data-linkage error, achieving 75–85% error reduction and producing publications in JRSS Series A and AISTATS.
• Optimized an MCMC algorithm with custom C code, reducing runtime by 90% relative to R and MATLAB baselines.

Ph.D.

George Mason University

Statistical Science

M.S.

Rutgers University

Statistics

B.S.

Arcadia University

Mathematics, Dean's Honor List