I care about the details that decide whether hardware actually ships.

I’m a Mechanical Engineering and EECS undergraduate at MIT (Class of 2027). I work across the full stack of a physical system: mechanical design and FEA, custom motor-control electronics, and the machine learning that turns noisy sensor data into decisions.

My work spans a precision-motion digital twin for a stealth-stage startup, a real-time machining-chatter detector in an MIT lab, and an autonomous tissue-targeting device at Brigham and Women’s Hospital. The through-line is de-risking hardware before it’s built — simulation that kills wrong hypotheses fast, and models precise enough to trust.

How I work

Mechanical & simulation. Static, modal, and harmonic FEA; multiphase CFD and thermal; parametric sweeps and mesh-independence studies — used to make a real design decision, not to make pictures. I’ve turned a failed 100 GB solve into a 34-second run so a team could iterate in a loop.

Electronics & controls. Custom motor-control hardware — field-oriented control, back-EMF sensing, thermal management — on multilayer boards, from a 6S FOC ESC to piezo motion at 10 nm resolution.

Perception & ML. Signal-only, CPU-only detectors that survive the gap between clean lab data and a real machine, plus computer-vision pipelines that replace slow manual work.