Cyrus Leung

Product Manger at Moovup 好工速遞

Hong Kong Island, Hong Kong, China
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
🎓
Top School
Cyrus Leung is a product manager and former product and UX leader with over a decade of experience bringing customer-focused digital products to market across fintech, e-commerce, and consumer platforms. Based in Hong Kong, he has led product and UX teams at YouTrip, Brightful, and now Moovup, blending hands-on design sensibilities with strategic product delivery. His background as a designer and early career roles in web and UX position him to translate user needs into polished, usable products while coaching cross-functional teams. Cyrus also contributes to open-source backend tooling—fixing bugs and improving async utilities for a high-throughput LLM inference project—showing a practical engineering chops beyond pure product work. Currently a PhD candidate at HKUST, he pairs academic rigor with startup execution, often spotting operational edge cases and API quirks before they reach customers.
code6 years of coding experience
job8 years of employment as a software developer
bookBachelor of Science - BS, Bachelor of Science - BS at The University of Texas at Austin
github-logo-circle

Github Skills (8)

asynchronous10
openai-api10
api10
python10
apidoc10
async10
llm10
tokenizer9

Programming languages (7)

TypeScriptHCLC++SCSSJavaScriptJupyter NotebookPython

Github contributions (5)

github-logo-circle
vllm-project/vllm

Apr 2024 - Apr 2025

A high-throughput and memory-efficient inference and serving engine for LLMs
Role in this project:
userBack-end Developer
Contributions:3050 reviews, 1202 PRs, 1179 pushes in 11 months
Contributions summary:Cyrus contributed to the project by moving utility functions related to asynchronous iterators to a separate module. They addressed bugs in the OpenAI API entrypoints, fixing issues with chat templates and extra fields in the API. The user also corrected a parameter name within the tokenizer, further contributing to improvements of the codebase and API functionality.
amdcudadeepseekgpthpu
DarkLight1337/vllm-rocm

Apr 2024 - Nov 2024

ROCm-enabled vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs
Contributions:2 PRs, 1306 pushes, 236 branches in 7 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.
Request Free Trial