Hi, I’m Chenxi Yang, a research scientist at Meta MSL working on efficient inference for large language models and multimodal AI systems.

I received my Ph.D. in Computer Science from University of Texas at Austin, advised by Swarat Chaudhuri, and my B.S. from Fudan University, working with Yang Chen and Chenren Xu. During the first year of my graduate studies, I also worked with Lili Qiu on video streaming systems for DNNs.

My research centers on building efficient, reliable, and scalable AI systems. During my Ph.D., I developed theory and tools (DSE, CAROL, Canopy) that provide performance and robustness guarantees for ML-driven controllers. I extended this line of work to large-scale production environments through two internships at Google, working on TPU optimization (SRG) and ML-based storage optimization, working with Yawen Wang, Elliot Li, Mustafa Uysal, and Martin Maas.

I like reading, playing tennis, hiking, and travelling.