Zeyu Wang
Pittsburgh, Pennsylvania, United States
Summary
🤩
RockstarZeyu Wang is an AI/ML engineer with seven years of experience building production-grade distributed systems, CI/CD platforms, and LLM tooling, currently working at Yahoo and pursuing advanced research at Carnegie Mellon University. He blends systems-level expertise in C++, Java, and Python with cloud and storage knowledge from teaching and research roles on deep learning runtimes and advanced cloud/storage courses. At Yahoo he shipped automated CI/CD infrastructure, CICD telemetry platforms, and prototyped agentic LLM tooling that integrates with internal logs and metrics to automate pipeline debugging and QA. His CMU research focuses on speculative inference and SLO-customized LLM serving, and he has authored kernel work for task-based DNN inference—signals of a rare combination of production engineering and cutting-edge ML systems research. Based in Irvine, CA, he is comfortable moving between hands-on implementation, developer enablement, and publications-driven research.
7 years of coding experience
Github Skills (21)
parallelization10
llama10
inference10
multimodal10
large-language-models10
reinforcement-learning10
llm10
cuda10
transformer10
minimax10
glm9
wan9
neural-network7
distributed-computing2
legion2
Programming languages (4)
Github contributions (5)
zwang86/sglang
Feb 2026 - Mar 2026
Contributions:1 PR, 19 pushes, 4 branches in 1 month
callMeBigBen/Aridac
Apr 2022 - May 2022
Contributions:19 pushes in 6 days
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.