I’m an analytics engineer and data scientist who builds infrastructure for messy data and applies statistical models to extract meaningful insights. Most of my work involves taking fragmented, inconsistent data sources and building platforms that make them actually usable for analysis. I work with the Center for Public Health Systems at the University of Minnesota, where I’ve built a platform that consolidates 400+ inconsistent federal data fields into 4M standardized records. I completed my MPH coursework in Public Health Data Science last May and I’m finalizing capstone deliverables. My background spans systems engineering, data infrastructure, biomedical research, and applied biostatistics.
The problems that interest me sit at the intersection of engineering and statistics. Systems are puzzles, but they’re real and constantly changing, which means the solutions can be creative rather than prescribed. You need to understand how data gets generated to model it correctly. You need infrastructure that can handle messy, heterogeneous sources before you can do meaningful analysis. Recent projects include building memory-efficient pipelines, engineering survival models with custom biomarker phenotypes, developing predictive models from longitudinal health data, and creating a distributed job aggregator using LLM-assisted parsing. I also build interactive statistical education tools and run a self-hosted infrastructure cluster for local LLM inference.