Summary
Stu Cao is a Senior Software Development Engineer and engineering lead with nearly a decade of experience building large-scale AI inference systems and distributed data platforms across cloud and embedded device domains. He has driven production ML deployments at Amazon—optimizing TensorRT/Triton inference engines for 2×+ performance gains, productionizing multi-modal LLMs, and scaling an IoT data pipeline ingesting 100K TPS from millions of vehicles. Earlier work at Apple delivered embedded power-system software that ships on hundreds of millions of iPhones and Watches, and his background in electrical engineering informs a systems-first approach to performance and reliability. Stu excels at bridging research and production, shortening model turnaround from weeks to days while enabling zero-downtime rollouts and enterprise-grade observability. He combines low-level kernel and hardware-aware optimization (Trainium, MXFP4/BWMM kernels) with cloud architecture and product delivery, making him adept at solving both scientific and operational problems. Based in Sunnyvale, he pairs technical depth with cross-functional leadership that turns prototypes into resilient, widely adopted services.
9 years of coding experience
11 years of employment as a software developer
Master's degree, Electrical and Electronics Engineering, Master's degree, Electrical and Electronics Engineering at Georgia Institute of Technology
BS, Electronic Engineering, BS, Electronic Engineering at Shanghai Jiao Tong University
English, Chinese, French