As InsightRX's first data science engineer, I developed production-ready services to serve pharmacokinetic and ML models, run data processing pipelines, and host web applications. I wrote and maintained docker images and CI/CD pipelines to ensure that our products were reliable, deployable, and met the rigorous requirements of the healthcare industry.

In my time at Sage Bionetworks I built software to allow researchers from over 50 studies to access, curate, validate, and share data in order to identify new drug targets for Alzheimer's disease. Select projects included an interactive data validation application and an app for scoring compounds for preclinical testing. I also led efforts to standardize metadata strategy for the organization and established a culture of code review and robust development practices for data scientists and researchers. As a principal engineer, I led a team of engineers to develop tools and computational infrastructure for mobile health applications and neurodegenerative disease research.

Developed features for ggplot2, including adding built-in support for new color scales and developing a new algorithm for placement of box plots. Conducted a major refactor of the mechanism underlying text placement on plots. Identified, diagnosed, and fixed bugs in the ggplot2 codebase.

Explored the relationship between food recalls and Amazon product reviews using supervised and unsupervised NLP techniques.

Assembled data from dozens of research groups for the first global quantitative analysis of under-ice lake ecology. Wrote software in R to validate and harmonize incoming data, ensuring that all data could be reproducibly integrated into a single consistent dataset. Developed CI pipelines with Travis-CI and AppVeyor to ensure code reliability.

Designed data management policies and practices for a study of the effects of climate change on the world's most biodiverse lake, Lake Baikal.