Wind Yuan
Principal Software Engineer at NVIDIA
Sunnyvale, California, United States
Summary
👤
Senior🎓
Top SchoolWind Yuan is a Principal Software Engineer with 14 years of deep expertise in computer vision, image processing, video codecs, and GPU-accelerated systems, now applying that background to multimodal sensor fusion and inference at NVIDIA. He originated and still maintains the influential open-source libxcam project, which brought real-time OpenCL-based image pipelines and automotive surround-view features upstream into AOSP. His work spans low-level codec and ISP integration to model deployment (Triton, TensorRT, PyTorch/ONNX) and LLM embeddings, showing a rare blend of embedded systems, cloud inference, and graphics (GLES) skills. Based in Sunnyvale, he pairs hands-on C++/Python engineering with mentoring and open-source stewardship, and outside work he’s an avid driver—reflecting a practical interest in automotive applications.
14 years of coding experience
15 years of employment as a software developer
Bachelor of Science (B.S.) Computer and Information Sciences, Bachelor of Science (B.S.) Computer and Information Sciences at Jiangnan University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (12)
c-language10
cprogramming-language10
image-processing10
v4l210
gstreamer9
opencl9
vulkan9
c178
c118
sys7
camera-calibration7
embedded7
Programming languages (3)
Github contributions (5)
intel/libxcam
Jan 2015 - Sep 2018
libXCam is a project for extended camera(not limited in camera) features and focus on image quality improvement and video analysis. There are lots features supported in image pre-processing, image post-processing and smart analysis. This library makes GPU/CPU/ISP working together to improve image quality. OpenCL is used to improve performance in different platforms.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:375 commits, 674 PRs, 558 pushes in 3 years 9 months
Contributions summary:Wind primarily contributed to the core functionality of the `intel/libxcam` repository, focusing on extended camera features and image quality improvements. Their work involved implementing and integrating image processing operations and analysis by modifying source files in the xcore directory to work with atomisp APIs. These commits demonstrate a strong understanding of software development and image processing techniques.
cameravideoimage-qualityopenclcpu
windyuan/libxcam
Mar 2015 - Aug 2018
Libxcam is a project for extended camera features, especially 3A process. It separates 3A algorithm and ISP image processor, and makes user defined algorithm possible. This framework is also trying to make GPU joining the image process.
Contributions:299 pushes, 15 branches, 2 comments in 3 years 6 months
definedextendedgpucameraimage-process
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.