Felix Lin is a seasoned AI infrastructure researcher and educator based in the San Francisco Bay Area with 13 years of experience spanning academia and industry. As Senior Research Scientist for AI Infrastructure at ByteDance and an Associate Professor at the University of Virginia, he specializes in model-and-system co-design for large language models and generative AI, focusing on practical real-time serving, on-device inference, and hardware-aware optimization. His work ranges from real-time speech model serving (arXiv:2412.11272) and on-device LLMs to memory-efficient stream analytics and the exploration of a new OS in 2025, reflecting a hands-on approach to bridging research with production-scale systems. He holds a PhD in Computer Science from Rice University, with prior professorship at Purdue University and advanced degrees from Tsinghua University (BS MS), demonstrating a strong foundation in both theory and applied engineering. His current research interests include optimizing LLMs for NPUs and quantized kernels for GPUs, underscoring a commitment to performance at scale in heterogeneous hardware. Based in the Bay Area, he brings a rare blend of academic rigor, industry pragmatism, and leadership in AI infrastructure.
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.