Resume
Academic Achievements
- Hardware-aware algorithms for ML: ThunderKittens, ThunderMLA, FlashAttention, FlashFFTConv; Efficient ML architectures: Chipmunk, Hungry Hungry Hippos, Monarch Mixer
Research Experience
- Current: Assistant Professor, Computer Science and Engineering Department, University of California, San Diego; VP of Kernels, Together AI; Previously: PhD, Department of Computer Science, Stanford University
Education
- PhD, Department of Computer Science, Stanford University
Background
- Research Interests: machine learning and systems, with a focus on efficiency. About Me: Building a world-class kernels team at Together AI; Assistant Professor at UCSD leading the SandyResearch Lab and affiliated with the MLSys group; VP of Kernels at Together AI, focusing on low-level performance engineering and GPU kernels.
Miscellany
- Links: Lab Website, How I Structure Introductions to Research Papers, The Coffee Experiment, Stanford MLSys Seminar (started during the pandemic)