Yaxing Cai
Senior System Software Engineer at NVIDIA
Shenzhen, Guangdong Province, China
Summary
🤩
Rockstar🎓
Top SchoolYaxing Cai is a Senior System Software Engineer based in Shenzhen with 10 years of experience building high-performance ML and systems software, currently at NVIDIA after OctoAI’s acquisition. He specializes in runtime and compiler internals—contributing to high-profile open-source projects like Apache TVM by unifying function types and improving logging and low-level execution paths. Yaxing also bridges mobile and backend work, having rebuilt the iOS UX and robust model download handling for the mlc-llm deployment engine. A USC MS graduate with a BE from Shanghai Jiao Tong, he combines deep systems engineering with practical product sensibility and a bias for shipping solutions quickly.
10 years of coding experience
2 years of employment as a software developer
Master of Science - MS Computer Science, Master of Science - MS Computer Science at University of Southern CaliforniaBachelor of Engineering - BE Computer Science, Bachelor of Engineering - BE Computer Science at Shanghai Jiao Tong University
Github Skills (23)
c-language10
ios10
url-encoding10
user-interface10
url-scheme10
url-validation10
url-parsing10
compiler-compiler10
compiler10
swift10
url-parser10
cprogramming-language10
architecture9
data-structure9
debug9
Programming languages (4)
Github contributions (5)
mlc-ai/mlc-llm
May 2023 - Nov 2024
Universal LLM Deployment Engine with ML Compilation
Role in this project:
Mobile Developer (iOS)
Mobile Developer (iOS)Contributions:34 reviews, 65 PRs, 15 pushes in 1 year 6 months
Contributions summary:Yaxing focused on implementing and improving the iOS application for the mlc-llm project. They addressed an issue with invalid input URLs for model downloads, ensuring the application can handle such cases gracefully. The user also overhauled the iOS app's user experience (UX), adding features like model clearing and deletion and finalizing state management within the application.
language-modelllmmachine-learning-compilationtvm
apache/tvm
Feb 2022 - Jan 2023
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Role in this project:Back-end Developer
Back-end DeveloperContributions:92 reviews, 46 commits, 122 PRs in 11 months
Contributions summary:Yaxing's commits primarily involve enhancing the runtime environment of the TVM project, specifically by integrating `PackedFunc` into the TVM object system to provide a unified function type and enhance the logging capabilities. They also made modifications to handle different data types and integrate low-level functions for optimized execution. This indicates a focus on the internal workings of the compiler and its runtime.
metalvulkancompilertensoropencl
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.