Yao Yao
Software Architect at Nvidia
Shanghai, China
Summary
🤩
RockstarYao Yao is a Software Architect and Principal Compute Architect at NVIDIA based in Shanghai with eight years of industry experience building high-performance compute solutions. He specializes in architecting scalable compute platforms and bridging deep technical design with practical implementation for accelerated workloads. Known for applying GPU compute expertise to complex system problems, he brings an engineer’s rigor to performance tuning and architecture decisions. Operating at the intersection of research-grade compute and production systems, he helps teams translate algorithmic requirements into deployable infrastructure. Colleagues appreciate his combination of hands-on technical depth and clear architectural vision across performance-critical projects.
9 years of coding experience
Github Skills (62)
anycast10
pytorch10
runtimes10
python10
tensorrt10
cereal10
bag-of-words10
inference10
large-language-models10
sift10
llm10
serialization10
nvidia10
cuda10
cpp10
Programming languages (8)
Github contributions (5)
lowsfer/cereal
Dec 2020 - Aug 2024
A C++11 library for serialization
Contributions:1 release, 1 PR, 5 pushes in 3 years 8 months
cppserializationheader-onlyserializercpp-library
lowsfer/TensorRT-LLM
Apr 2025 - Jul 2026
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
Contributions:92 pushes, 19 branches in 1 year 3 months
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.