Summary
Baizhou Zhang is a software engineer focused on AI inference infrastructure with five years of experience building high-performance ML systems and tooling. As a core developer and maintainer of SGLang at RadixArk, he architects deterministic inference, attention kernels, large-scale execution plans, and CI/CD for modern model deployments. His internships at NVIDIA (CuDNN heuristics), Baidu (CINN), and contributions to ColossalAI give him practical fluency across GPU kernels, compilers, and distributed training. Combining research experience in model quantization and VAE music generation with a UC San Diego MS and a Peking University BS, he aims to be an AI-infra full-stack engineer who bridges low-level kernel work to production inference pipelines. An inquisitive "novice of building systems," he brings hands-on open-source stewardship to ambitious, performance-sensitive ML stacks.
5 years of coding experience
1 year of employment as a software developer
Visiting Student, Computer Science, Visiting Student, Computer Science at University of California, Berkeley
University of California, San Diego
Bachelor of Science - BS, Intelligence Science and Technology, Bachelor of Science - BS, Intelligence Science and Technology at Peking University