Yanchao Lu
Senior Compute Arch Manager at NVIDIA
Pudong, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolYanchao Lu is a senior compute architecture leader at NVIDIA, specializing in TensorRT core libraries, LLM inference infrastructure, and backend performance optimization. With a PhD in Computer Science from Shanghai Jiao Tong University and a dual technical and business undergraduate background, he blends deep research rigor with product-minded system design. He progressed through roles from Compute Architect to Senior Compute Arch Manager, driving TensorRT release engineering and inference performance across multiple generations. Early experience as a startup co-founder and research stints at Microsoft Research Asia and Nanyang Technological University give him a rare mix of entrepreneurial initiative and academic depth. Based in Pudong, Shanghai, he focuses on turning cutting-edge model capabilities into production-grade, high-performance inference systems.
2 years of coding experience
9 years of employment as a software developer
Bachelor of Engineering - BE, Computer Science and Technology, Bachelor of Engineering - BE, Computer Science and Technology at Beijing Institute of TechnologyDoctor of Philosophy - PhD, Computer Science and Technology, Doctor of Philosophy - PhD, Computer Science and Technology at Shanghai Jiao Tong UniversityProgramming languages (2)
Github contributions (5)
NVIDIA/TensorRT-LLM
Mar 2024 - Apr 2025
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:28 reviews, 9 PRs, 9 pushes in 1 year
chzblych/TensorRT-LLM
Mar 2025 - Mar 2025
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:1 push, 5 branches in 1 day
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.