Yiran Wu
PhD Candidate
State College, Pennsylvania, United States
Summary
🤩
Rockstar🎓
Top SchoolYiran Wu is a PhD candidate in Informatics at Penn State with seven years of software engineering experience focused on AI agents and applied ML. She has interned twice at Microsoft, where she trained RL-based software agents and built the first benchmark for LLM agents in cybersecurity investigations, including a novel graph-to-question generation method and a MySQL-backed evaluation environment. Her open-source work includes implementing a MathChat agent within Microsoft's popular Autogen framework, enhancing its math-solving pipeline and documentation. With an MS in AI & Machine Learning from Imperial College and a BS in Computer Science from UC Davis, she blends rigorous academic research with practical engineering. Yiran’s strengths lie in translating research ideas into reproducible benchmarks and agent implementations that surface fine-grained failure modes. Colleagues note she often uncovers subtle evaluation gaps that lead to more robust agent behaviors.
7 years of coding experience
Bachelor's degree Computer Science, Bachelor's degree Computer Science at University of California, DavisDoctor's Degree Informatics, Doctor's Degree Informatics at Penn State UniversityMaster of Science - MS Artificial Intelligence & Machine Learning, Master of Science - MS Artificial Intelligence & Machine Learning at Imperial College London
Github Skills (11)
llm10
autogen10
agent10
ai-agent10
python10
agentic10
math9
mathematics9
app-framework9
application-framework9
web-framework9
Programming languages (3)
Github contributions (5)
microsoft/autogen
Sep 2023 - Aug 2024
A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1 release, 121 reviews, 46 PRs in 11 months
Contributions summary:Yiran primarily implemented a "MathChat" agent within the Autogen framework. Their contributions included implementing the core logic for the MathChat agent, code formatting, and updates to the `readme` and configuration files. The user appears to have focused on integrating and refining the math-solving capabilities within the Autogen framework. These changes involved modifying a Python file to provide the agent math capabilities
agenticagentic-agiagentsaiautogen
ag2ai/build-with-ag2
Jan 2025 - Mar 2025
Sample code and application showcases to get you going with AG2 (formally AutoGen)
Contributions:21 reviews, 20 PRs, 40 pushes in 2 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.