Yifu Wu
Software Engineer at Amazon Web Services (AWS)
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolYifu Wu is a software engineer with 11 years of experience, currently contributing to AWS Cognito after multiple internships at AWS and a MS in Computer Science from USC. He blends back-end engineering and ML systems expertise, having improved serving infrastructure, benchmarking, and async error handling for the universal LLM deployment engine mlc-llm and added TensorFlow import and ops support to the widely used Apache TVM compiler. Based in Seattle, he brings practical production experience from both research and startup environments, including ML compiler and LLM engine co-design work with NVIDIA-affiliated projects. Known for curiosity and continuous learning, he often focuses on observability and performance—enhancing metrics, CUDA profiling, and reset/error mechanisms to make complex ML systems more robust.
11 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 Science - BS, Electrical & Computer Engineering, Bachelor of Science - BS, Electrical & Computer Engineering at University of Washington
Github Skills (18)
asynchronous10
benchmark10
language-model10
python10
async10
benchmarking10
llm10
relayer10
compiler-compiler10
mlops10
tensorflow10
compiler10
relay10
machine-learning9
documentation9
Programming languages (9)
Github contributions (5)
apache/tvm
Oct 2018 - Sep 2020
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Role in this project:
Back-end Developer
Back-end DeveloperContributions:306 reviews, 31 commits, 154 PRs in 1 year 11 months
Contributions summary:Yifu's contributions focused on enhancing the documentation and functionality of the Apache TVM compiler stack, particularly in the Relay module. The user updated documentation related to Relay operations, and added support for TensorFlow saved model import. Furthermore, they implemented support for several TensorFlow operations including Gather, Where, Tile, Round, Sign, Pow, Exp, Reverse, and others.
metalvulkancompilertensoropencl
mlc-ai/mlc-llm
May 2023 - Mar 2025
Universal LLM Deployment Engine with ML Compilation
Role in this project:MLOps Engineer
MLOps EngineerContributions:5 reviews, 17 PRs, 11 comments in 1 year 10 months
Contributions summary:Yifu primarily focused on improving the serving infrastructure and benchmarking of the ML model deployment engine. They addressed issues related to server configuration, added CUDA profiling to benchmark tests, and implemented error handling within the engine's asynchronous processing. Their contributions also included adding functionality to reset the engine and enhancing the metrics collected to provide more detailed insights into the system's performance.
language-modelllmmachine-learning-compilationtvm
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.