Bo Li

AI Compute DevTech Engineer at NVIDIA

Zurich, Zurich, Switzerland
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Bo Li is an AI Compute DevTech Engineer at NVIDIA with nine years of graphics and simulation-focused software engineering experience, currently contributing to TensorRT-LLM. Trained at Peking University and ETH Zürich, he blends real-time rendering expertise with physics-based simulation—having implemented probe-based GI and ported advanced rendering techniques to mobile at Tencent and worked on PBD/IPC soft-body and cloth systems during internships at NVIDIA and Disney Research. He excels at squeezing performance from engines and hardware, with a track record of profiling, optimization and scalable illumination solutions for open-world scenes. Based in Zurich, he brings a rare combination of production graphics engineering and academic rigor, and often bridges research ideas into practical, high-performance implementations.
code9 years of coding experience
job2 years of employment as a software developer
bookBSc, Computer Science and Technology, BSc, Computer Science and Technology at Peking University
bookMSc, Computer Science, MSc, Computer Science at ETH Zürich
github-logo-circle

Github Skills (33)

pytorch10
robotics10
runtimes10
python10
tensorrt10
inference10
large-language-models10
llm-inference10
llm10
kernel10
nvidia10
gpu10
cuda10
cpp10
jit10

Programming languages (5)

C++CMakeJavaScriptPythonCuda

Github contributions (5)

github-logo-circle
ethz-pbs21/SandyFluid

Nov 2021 - Feb 2022

Contributions:44 commits, 1 PR, 4 pushes in 3 months
bobboli/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:301 pushes, 73 branches in 1 year 3 months
cppinferencelarge-language-modelsllmnvidia
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.
Request Free Trial