Biomedical engineering student on the computational track at UT Austin. I work on physiological signals and the models that interpret them, and I try to run those models on the device that recorded the signal.

B.S. May 2027 · Austin, TX

Clinical AI on the phone

The app's recording screen

Stealth Clinical AI

2026

An on-device language model that evaluates clinical conversations for an early-stage startup. Qwen 3.5-4B in under 500 MB of RAM.

A Localabs report summary

Localabs

2026

Turns a photo of a lab report into a plain-language explanation in about 12 seconds, with MedGemma 4B running on the phone.

The Scribend SOAP note screen, recreated from the app's code

Scribend

2026

An offline medical scribe, built at the Qualcomm × Meta ExecuTorch Hackathon, that writes a SOAP note from a clinic visit on the phone.

Signals and embedded

Cloud to Edge Heart Rate Monitor

2025–26

A Raspberry Pi 5 streams ECG recordings to a Pico, which classifies each heartbeat with a neural network written in C while its second core acts as a watchdog.

Longhorn Neurotech

2024–

Edge AI Team Lead. Our EMG gesture model runs 2.4× faster on a Raspberry Pi Zero 2 W after INT8 quantization, at 311 KB.

Two game boards mid-race

Embedded Multiplayer Racer

2025

A two-player racing game in bare-metal C on two TI MSPM0 boards, kept in sync over UART. Voted Best Game in ECE 319K.

The purple ECG circuit board

ECG PCB

2025

An ECG board built with two classmates that produced a clean trace in LabVIEW, using an AD620 amplifier and 0.32 to 39 Hz filtering.

Research tools

Laser mount and camera on an optical table

Laser Speckle Imaging

2023–25

Real-time 16-bit speckle contrast over a 7×7 window, with closed-loop laser current control.

Two spike clusters in phy's 3D feature view

phy 3D Feature View

2025

A 3D view for an open-source spike-sorting tool, built at the Recanzone Lab, UC Davis.