Yixin Nie is a Research Scientist at Meta with a decade of experience building and evaluating conversational AI and ML systems. He holds a PhD in Computer Science from UNC Chapel Hill and earlier degrees from The University of Chicago and China University of Geosciences, blending strong academic foundations with practical research impact. At Meta and in open-source projects like ParlAI, he contributes across the full stack—implementing dataset integrations, fixing MTurk workflows, and improving build and documentation processes—demonstrating both engineering breadth and ML depth. His GitHub persona, "a human in the maze," reflects a curiosity-driven approach to complex dialogue systems and tooling. Based in Sunnyvale, CA, he is comfortable moving between research prototypes and production-ready integrations, with a particular knack for dataset engineering and reproducible evaluation.
10 years of coding experience
5 years of employment as a software developer
Bachelor's degree, Computer and Information Security, Bachelor's degree, Computer and Information Security at China University of Geosciences
Master's degree, Computer Science, Master's degree, Computer Science at The University of Chicago
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of North Carolina at Chapel Hill
A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
Role in this project:
Full-stack Developer & ML Engineer
Contributions:8 commits, 8 PRs, 3 branches in 2 years 1 month
Contributions summary:Yixin contributed to multiple areas within the ParlAI framework, showcasing a broad skillset. They fixed a bug in the MTurk qualification flow, updated the build process for new file types, and added support for a new dataset (DECODE) by implementing associated agents and build configurations. Further, they addressed issues related to project documentation and dataset cleaning, highlighting a focus on the overall project development, integration, and maintenance.
This repository provides the implementation for the paper "Combining Fact Extraction and Verification with Neural Semantic Matching Networks".
Contributions:27 commits, 1 PR, 25 pushes in 2 years 9 months
pytorchnlpextractionfactmatching
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.