
VP of Kernels at Together AI and Assistant Professor of Computer Science and Engineering at UC San Diego, focused on efficient machine learning systems and GPU performance.
Dan Fu is VP of Kernels at Together AI (and an incoming assistant professor at UC San Diego), leading a team focused on low-level GPU performance engineering. A co-author of FlashAttention and a creator of the ThunderKittens kernel DSL, he offers direct insight into state-of-the-art kernel engineering for fast AI inference on modern hardware.
Public activity researched automatically · as of Jun 2026