Xin Yao
Principal Member Of Technical Staff at GlobalFoundries
City of Schenectady, New York, United States
Summary
🤩
Rockstar🎓
Top SchoolXin Yao is a Principal Member of Technical Staff with 11 years of semiconductor product and yield engineering experience and a career spanning foundry management, product qualification, and test engineering from 0.18um Flash to 14nm FinFET. He has led cross-functional teams and external foundry partners to diagnose process issues, improve baseline yield, and shepherd GPU/CPU, ASIC and Flash products through NPI to production. Skilled in JMP, SPC, DOE, FMEA and change management, Xin combines deep hands‑on process expertise with program management and ASQ-certified quality rigor. He also contributes GPU-focused work to open-source ML tooling—implementing CUDA and UVA support for graph deep learning data paths—bringing practical hardware-aware performance improvements to software projects. Based in Schenectady, Xin pairs technical leadership with a business perspective from an MBA, making him effective at translating complex process challenges into production-ready outcomes.
11 years of coding experience
9 years of employment as a software developer
M. Sci. Microelectronics, M. Sci. Microelectronics at Science Academy of ChinaB.Sci. Microelectronics, B.Sci. Microelectronics at Jilin UniversityMaster of Business Administration - MBA, Master of Business Administration - MBA at Nanyang Technological University Singapore
English, Chinese
Github Skills (8)
cuda10
gpu-programming10
pytorch10
deep-learning10
graph-neural-network10
performance-optimization10
python10
unit-test9
Programming languages (9)
Github contributions (5)
dmlc/dgl
Oct 2021 - Jan 2023
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Role in this project:
ML Engineer
ML EngineerContributions:265 reviews, 55 commits, 157 PRs in 1 year 2 months
Contributions summary:Xin's primary contributions focused on implementing GPU-based functionality for the DGL library, a deep learning on graphs package. Their work included implementing `dgl.compact_graphs()` for GPU usage and introducing CUDA implementations to support edge and node subgraph operations, with additional work on adding the ability for UVA based sampling and integration into existing data loading functionalities. They fixed and improved test cases while making changes to the underlying code to make the library compatible with various GPU and CPU setups. The contributions involve performance improvements and better support for different hardware configurations.
pytorchpythondeep-learningmachine-learninggraph-neural-networks
yaox12/TransformerEngine
Nov 2023 - Apr 2025
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
Contributions:176 pushes, 30 branches in 1 year 5 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.