Jun Liu
Irvine, California, United States
Summary
🤩
Rockstar🎓
Top SchoolJun Liu is an experienced engineer with a PhD in Electrical Engineering and over 3 years in industry roles focused on computer vision, signal processing, and embedded systems, currently working at NVIDIA in Irvine. He has led and shipped VIO/SLAM and monocular depth estimation solutions, contributed to ultrasound beamforming and real-time video surveillance, and holds multiple patents in depth and imaging technologies. Proficient in C/C++, MATLAB, Python test automation, OpenCV/OpenGL, and low-level networking, he blends rigorous algorithm development (FFT, harmonic retrieval, beamforming) with practical product engineering. Jun’s background spans startups and major corporations—from designing diagnostic ultrasound hardware to optimizing smartphone camera and VR power—demonstrating an unusual combination of academic research and hands-on system integration. Known for strong literature survey skills and novel algorithm design, he also has a track record of turning research prototypes into deployed modules, such as a VIO component used in commercial products.
2 years of coding experience
23 years of employment as a software developer
Phd, Electrical Engineering, GPA 3.97, Phd, Electrical Engineering, GPA 3.97 at University of LouisvilleMaster, Information and Electrical Engineering, Master, Information and Electrical Engineering at Huazhong University of Science and Technology
Github Skills (19)
gnn9
sparse7
clustering6
building-blocks6
statistics5
nearest-neighbors5
machine-learning4
graph4
cuda4
science4
gpu3
information-retrieval3
linear-algebra3
graph-data-science3
llm2
Programming languages (3)
Github contributions (5)
hello-11/wholegraph
May 2023 - Jan 2024
Contributions:17 pushes, 12 branches in 7 months
NVIDIA/TensorRT-LLM
May 2024 - 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:2 reviews, 164 comments, 104 issues in 9 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.