Chao Xie
Principal Software Engineer at Meta
San Francisco Bay Area United States
Summary
🤩
Rockstar🎓
Top SchoolChao Xie is a Principal Software Engineer based in the San Francisco Bay Area with six years of professional experience building high-throughput ML serving and data infrastructure at Meta and Google. He has driven architecture and productionization for Ads ML serving and large-scale online ML workloads, helping serve hundreds of millions of queries per second across diverse hardware. His background includes building stateful, low-latency data pipelines that processed millions of events per second and supported multi-petabyte state for ads attribution systems. An author of infrastructure-focused contributions to the widely used tensorflow/serving project, he emphasizes deployability, performance monitoring, and reproducible builds (including CUDA and Docker improvements). Trained as a distributed systems researcher with a Ph.D. from UT Austin and a B.E. from Tsinghua, he blends rigorous academic grounding with pragmatic, production-first engineering. Colleagues describe him as an operator-engineer who finds elegant system-level fixes that unlock measurable revenue and reliability gains.
6 years of coding experience
9 years of employment as a software developer
The University of Texas at AustinB.E., Computer Science & Technology, B.E., Computer Science & Technology at Tsinghua University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (11)
docker10
mlops10
tensorflow10
serve10
dockers10
build-automation9
machine-learning9
devops8
python7
deep-learning6
cpp6
Programming languages (2)
Github contributions (5)
tensorflow/serving
Sep 2019 - Jan 2022
A flexible, high-performance serving system for machine learning models
Role in this project:
MLOps Engineer
MLOps EngineerContributions:7 releases, 1 review, 53 commits in 2 years 4 months
Contributions summary:Chao's commits primarily focus on the infrastructure and deployment aspects of the TensorFlow Serving system. They addressed dependencies, updated build configurations, and made internal changes related to the Docker build process. The user also contributed to the addition of metrics for runtime latency, indicating a focus on performance monitoring and optimization of the serving infrastructure. Furthermore, they updated CUDA versions and pinned dependencies, demonstrating an understanding of the system's environment and build process.
cpppythonservingdeep-learningml
shadowdragon89/serving
Oct 2019 - Apr 2021
A flexible, high-performance serving system for machine learning models
Contributions:4 PRs, 9 pushes, 10 branches in 1 year 6 months
servingmachine-learningperformancehigh-performancemachine-learning-models
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.