Research
Most of my research is about what an algorithm can do once the hardware sets the budget: how much of a model survives quantization, and how fast a channel estimate can come out of an FPGA.
Santa Clara University, Wireless Intelligent Networks (WIN) Lab
Research assistant
July 2025 to present, Santa Clara, California
- I investigate FPGA-based acceleration for machine-learning algorithms in high-throughput, low-latency workloads.
- I train and quantize models in PyTorch and TensorFlow, then port them to fixed-point FPGA implementations.
- I prototype and optimize FPGA implementations of wireless-communication algorithms, including signal processing and channel estimation.
BALANCE article
BALANCE: A Nonbinary Approach to Biomechanical Assistive Legs for Diverse Mobility Needs
Youth Innovation Journal, fall 2025, published 29 October 2025. I co-authored it with a student team as one of ten authors.
The article describes the BALANCE design and is separate from the provisional patent filing, No. 63/743,085.
UC Berkeley College of Engineering, ROAR Academy
Summer 2025
I trained in machine-learning systems, programmed them, and applied them to autonomous robotics, on a full scholarship.
A related ROAR SimRace submission provides a working solution for the Robot Open Autonomous Racing simulation series (Python).