Woosuk Kwon is co-founder and CTO of Inferact and co-creator of vLLM, an open-source engine for large language model inference. Before Inferact, he was a member of technical staff at Thinking Machines Lab and a research scientist at Google DeepMind. He earned his PhD in computer science at UC Berkeley, advised by Ion Stoica, and bachelor's degrees in computer science and engineering and mathematical sciences at Seoul National University.