Yuhang Ning is an ML performance engineer based in San Jose with six years of experience optimizing GPU-backed machine learning workloads across industry leaders. He has driven end-to-end performance tuning for large models like Google's Gemini family and worked on cycle-level GPU hardware-software co-design at NVIDIA’s Blackwell program. His background spans compiler and driver-level triage, CUDA optimization, and practical ML model improvements—bridging deep systems knowledge with applied ML from internship work at Apple and Xiaomi to production-scale engineering. Notably, he implemented a Transformer decoder + MoE recommendation model that materially improved offline and online metrics, reflecting both research chops and product impact. Yuhang combines academic experience at the University of Michigan with hands-on chip bring-up and performance debugging, making him adept at diagnosing bottlenecks from silicon to model. He’s an engineer who blends low-level GPU expertise with real-world ML deployment results.
6 years of coding experience
4 years of employment as a software developer
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at University of Michigan College of Engineering
International Baccalaureate
Computational and Applied Mathematics, Computational and Applied Mathematics at AwesomeMath Summer Camp
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.