I'm a Data Scientist II at UT Southwestern Medical Center (O'Donnell School of Public Health) in Dallas, TX. My work spans biomedical research software, AI infrastructure, cloud computing, and multi-omics analysis.
I work on the infrastructure that lets AI and scientists do research together without the work quietly corrupting itself. I care about provenance, observability, and verification: where results come from, how agents reach them, and what evidence supports them.
Software has tests; biology mostly doesn't. Point an optimizer at a goal with no honest verifier, and it gets good at plausible, fluent, quietly wrong answers faster than anyone can check them. Closing that gap is the work.
Building
Research agents that carry their evidence. Models will keep outgrowing whatever scaffolding we build to help them think, but they can't recover what was never written down. So this workbench doesn't think for the model: it runs the real analysis, records what each conclusion rests on, and keeps every judgment, human or model. Not yet public.