Currently a senior at UC San Diego studying computer science, focused on ML + systems. I'm broadly interested in
and the ML acceleration stack toward building intelligence for the physical world.
I'm excited about everything from pretraining and model architectures to efficient inference and physics-grounded benchmarks.
Most of my time right now is spent working with the
and
NVIDIA Research,
and contributing to
.
At
Hao AI Lab,
I'm working on inference and physics metrics for video and world models.
FastVideo
is an open-source framework for accelerating large-scale video generation through efficient post-training, distillation, and serving.
Previously, I've interned with the Autopilot team at
and the
PyTorch
acceleration team at
.
At
Tesla AI,
I worked on SOTA 3D foundation models, GPU kernels, and training performance that powered FSD and Optimus.
At
Meta,
I helped build out the runtime software stack for next-generation training and inference chips powering recsys and ads models at scale.