A preeclampsia risk system for rural India, built around a three-tier explainability layer for clinicians, ASHA workers, and mothers-to-be.
software engineer · rural-health ML · finland alum
I build software systems that turn messy, real-world data into decisions people can act on.
Right now that means a production maternal-health risk system in rural India, a full-time engineering role, and a running case for research-oriented graduate study abroad, built one shipped thing at a time.
Currently shipping
all projects →Research
all research →A pre-registered 240-condition synthetic experiment testing whether historical decision consistency predicts which of two classification mechanisms should be chosen.
Formalizes what happens when a messaging account's history splits across two devices with no way to recombine them, and proposes CARTA, a reconstruction contract that quarantines and reports what it can't safely resolve.