Builder, scientist, leader.

I'm a research and engineering leader at Stanford University, where I lead technical development of ROAR, a scientifically validated reading assessment platform used by real schools and districts across the country. What makes ROAR distinctive is the research-practice partnership at its core: every assessment is grounded in peer-reviewed science, and every deployment solves real problems in real classrooms. I built and manage the engineering team, the assessment delivery infrastructure, and the data/analytics pipelines that power the research.

Before Stanford, I was a data science postdoc at the UW eScience Institute, where I built open-source tools for reproducible neuroimaging analysis, including pyAFQ (published in Nature Methods), Cloudknot (serverless batch computing on AWS), Groupyr (sparse group lasso, published in JOSS), and AFQ-Insight (interpretable ML for tractometry, published in PLOS Computational Biology).

My PhD is in computational nuclear physics from the University of Washington, where I developed high-performance Monte Carlo simulations on DOE supercomputers as a Computational Science Graduate Fellow. The work resulted in a Physical Review Letters publication and gave me deep expertise in statistical methods, large-scale computing, and building software that has to be correct.

Before grad school, I served as a U.S. Peace Corps health education volunteer in Morocco, where I led community health infrastructure projects and co-organized the country's first national English spelling bee. Before that, I was an Air Force officer and systems engineer at the Space and Missile Systems Center.

I care about building things that are rigorous enough for science and practical enough for real-world deployment. I contribute to open-source scientific software and believe in reproducible, transparent research.