Shunyu Yao
Research Scientist at OpenAI
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolShunyu Yao is a research scientist at OpenAI with eight years of experience building and evaluating language-model-driven systems, grounded in a PhD in Computer Science from Princeton. His background spans top-tier research internships at Google, Microsoft, MIT-IBM, and CSAIL, and long-term work in Princeton’s NLP group where he taught advanced NLP courses. He has hands-on ML engineering experience contributing to influential open-source work such as the ICLR 2023 ReAct project, integrating QA environments and model evaluation pipelines. Based in San Francisco, he combines deep academic rigor with practical engineering—comfortable shipping reproducible experiments and environment integrations that bridge research and applied model development. An uncommon strength is his track record of moving from notebook-level prototyping to production-ready tooling across diverse research codebases.
8 years of coding experience
5 years of employment as a software developer
Bachelor's degree Computer Science, Bachelor's degree Computer Science at Tsinghua UniversityDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Princeton University
Github Skills (7)
large-language-models10
reasoning10
python10
natural-language-processing9
machine-learning9
nlp9
jupyter-notebook8
Programming languages (6)
Github contributions (5)
ysymyth/ReAct
Nov 2022 - Jan 2023
[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models
Role in this project:
ML Engineer
ML EngineerContributions:10 commits, 1 PR, 5 pushes in 2 months
Contributions summary:Shunyu contributed to the project by implementing and integrating machine-learning-related components. The commits include modifications to `hotpotqa.ipynb` and `FEVER.ipynb`, suggesting the user was involved in developing and testing models for question-answering tasks. The user also appears to have set up the environment and integrated libraries like `wikienv` and `wrappers` for interacting with the task environment.
decision-makinglarge-language-modelsllmprompting
princeton-nlp/tree-of-thought-llm
May 2023 - Jan 2025
[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Contributions:2 releases, 8 PRs, 35 pushes in 1 year 8 months
large-language-modelsllmpromptingtree-of-thoughtstree-search
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.