Li Yu
Guangzhou City, Guangdong Province, China
Summary
🤩
Rockstar🎓
Top SchoolLi Yu is a seasoned software engineer with 11 years' experience building high-performance Android systems and developer infrastructure across major Chinese tech firms including ByteDance and Alibaba. He specializes in performance optimization, reliability engineering, and developer productivity—having led platform-level projects like client performance analysis, AIOps for server issue localization, and quality-of-release tooling. Li has deep systems roots from Meizu and telecom R&D, and has taken teams from 0→1 with modern stacks (Kotlin, Jetpack, MVVM) and video playback integration to improve user retention. Recently he contributed significant full‑stack work to an open-source AI-powered PR review tool (qodo-ai/pr-agent), adding model integrations and inline review features that bridge ML and developer workflow. Based in Guangzhou, he combines rigorous "deep work" discipline with a practical focus on reducing single-person and technical dependencies by codifying processes and automation. Curious about generative AI and K-line analysis, he blends low-level systems expertise with emerging AI-enabled developer tools.
11 years of coding experience
3 years of employment as a software developer
硕士, 通信与信息系统, 87.4, 硕士, 通信与信息系统, 87.4 at Jinan University学士, 信息工程, 88.6, 学士, 信息工程, 88.6 at 北京理工大学
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (9)
pullrequest10
gpt10
openai10
python10
code-review10
git9
configuration-management9
devtools8
langchain8
Programming languages (13)
Github contributions (5)
The-PR-Agent/pr-agent
Jul 2023 - Apr 2025
🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:44 reviews, 3 PRs, 20 comments in 1 year 9 months
Contributions summary:Li made significant contributions to the `pr-agent` repository, focusing on improving the codebase, configuration, and AI model integration. They standardized Python code formatting, enhanced configuration loading, and added a new AI model ("ollama/llama3"). The user also modified the core PR reviewer functionality, adding inline comments, and incorporating labels. These changes enhance the tool's functionality.
openaipull-requestpull-requestscoding-assistantdevtools
barnett-yuxiang/prompt-engineering
Aug 2024 - Jul 2026
A comprehensive collection of prompts, strategies, and best practices for effectively utilizing large language models (LLMs).
Contributions:1 release, 4 reviews, 74 PRs in 1 year 11 months
context-engineeringflow-engineeringprompt-engineering
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.