Yuyan Zhang
Senior Software Engineer at Meta
Menlo Park, California, United States
Summary
👤
Senior🎓
Top SchoolYuyan Zhang is a Senior Software Engineer based in Menlo Park with a strong full‑stack and front‑end leadership background across Meta, Lyft, and Microsoft. Over four years of professional experience in senior and tech‑lead roles, she combines deep expertise in TypeScript/React and GraphQL with backend skills in .NET, Node.js, RESTful APIs and distributed systems design. Known for rigorous object‑oriented design and algorithmic thinking, she has led roadmap planning, onboarding, and cross‑functional delivery for developer portals, business tooling, and meeting apps. She also contributes to ML engineering in open‑source—integrating a FiGNN graph neural model for CTR prediction into the RecBole recommendation library—showing a knack for bridging frontend product work with ML systems. A collaborative communicator and mentor, she routinely unblocks teams and elevates junior engineers while shipping accessible, internationalized user experiences. Her background in electrical engineering and a master’s in software engineering bring both systems-level depth and pragmatic product focus.
4 years of coding experience
8 years of employment as a software developer
Bachelor's Degree Electrical and Electronics Engineering, Bachelor's Degree Electrical and Electronics Engineering at Hunan UniversityMaster's Degree Computer Software Engineering, Master's Degree Computer Software Engineering at Boston University
English, Chinese
Github Skills (9)
pytorch10
deeplearning-ai10
recommendation-system10
deep-learning10
graph-neural-network10
python10
modeling10
implement10
machine-learning9
Programming languages (1)
Github contributions (5)
RUCAIBox/RecBole
Oct 2022 - Nov 2022
A unified, comprehensive and efficient recommendation library
Role in this project:
ML Engineer
ML EngineerContributions:19 commits, 4 PRs in 13 days
Contributions summary:Yuyan primarily contributed to the implementation of the FiGNN model, a graph neural network approach for CTR prediction, within the RecBole framework. Their work involved adding the FiGNN model files, incorporating it into the context-aware recommender module, and creating associated documentation and test cases. These commits demonstrate a focus on integrating and testing a new recommendation model leveraging graph-based feature interaction techniques.
pytorchrecommenderdeep-learningcollaborative-filteringsequential-recommendation
CIEEMio/Personal-Note-CAU-keep-alive
Jun 2022 - Jul 2023
Contributions:32 pushes in 1 year 1 month
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.