Ziqi Fan
Software Engineer (IC5) at NVIDIA
Sunnyvale, California, United States
Summary
🤩
Rockstar🎓
Top SchoolZiqi Fan is a senior system software engineer specializing in distributed systems, large-scale ML/LLM infrastructure, and GPU-optimized model serving, currently contributing to NVIDIA Triton Inference Server. With a Ph.D. in Computer Science and experience across LinkedIn ML infra, Uber’s Michelangelo platform, and deep-learning systems at NovuMind, he bridges research-level rigor with production-grade engineering. He has hands-on expertise enabling NLP/LLM training and efficient GPU serving, plus practical experience in storage and in-storage computing from early roles. Based in Sunnyvale, CA, Ziqi combines systems-level performance tuning with applied ML inference work—an uncommon blend that surfaces in contributions to LLM inference tooling and NVIDIA Dynamo-related projects.
1 year of coding experience
7 years of employment as a software developer
Ph.D., Computer Science, Ph.D., Computer Science at University of MinnesotaB.S., Computer Science, B.S., Computer Science at Dalian University of Technology
English, Chinese
Github Skills (35)
kubernetes10
pytorch10
data-center10
preprocess10
machine-learning10
inference10
llm-inference10
deep-learning10
gpu10
cuda10
rust10
reinforcement-learning9
amd9
llm9
llama9
Programming languages (3)
Github contributions (5)
ryanolson/vllm
Jun 2025 - Jul 2025
A high-throughput and memory-efficient inference and serving engine for LLMs
Contributions:2 reviews, 7 PRs, 5 pushes in 21 days
ziqifan617/vllm
Dec 2025 - Jun 2026
Contributions:3 pushes, 1 branch in 6 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.