AI strategy, cloud research platforms, and engineering standards for clinical trials, grounded in biostatistics and 15+ years of R.
🧠 Head of Applied Intelligence at the Prostate Cancer Clinical Trials Consortium, where I own our AI strategy and the cloud research platform behind it, and lead the organization through safe, effective LLM adoption
🏗️ Building open-source clinical trial systems (EDC, eTMF, randomization, biobanking, safety) with 21 CFR Part 11 controls enforced in the database, and agentic coding workflows that hold up in regulated environments
🎓 Trained biostatistician and epidemiologist (ScD, Harvard)
📕 Co-author of Causal Inference in R (CRC Press)
| 🚀 Building now | 🧰 Open source highlights |
|---|---|
| ducklake: tidyverse interface to DuckLake, the DuckDB lakehouse format (on CRAN) | ggconsort: CONSORT diagrams in ggplot2 |
| dplyneage: column-level lineage diagrams for dplyr and dbplyr pipelines (on CRAN) | ggswimlane: clinical trial swimlane plots in ggplot2 |
| ltsummary: the gtsummary interface with two dependencies instead of 62, for validated computing environments | r-code-review-checklist: a code review checklist template for R teams |
🎤 posit::conf(2026): Quack to the Future, building traceable data lakehouses with DuckLake in R