Chendi Xue
Machine Learning Engineer at Intel Corporation
Austin, Texas, United States
Summary
🤩
Rockstar🎓
Top SchoolChendi Xue is a Machine Learning Engineer with 12 years of experience building high-performance cloud and ML infrastructure, currently focused on scalable LLM serving, AI agents, and recommender system solutions at Intel in Austin. He blends deep systems expertise—Linux kernel, Ceph, persistent memory, Spark/Arrow—with applied ML skills in GNNs, NAS, and feature/training/inference optimization to squeeze latency and cost from real-world workloads. Notably, he contributed CI/CD and HPU-specific validation for the popular vLLM project, enabling LLM inference on Habana hardware. His background includes design and delivery of storage and shuffle optimizations, Spark native vectorization work, and benchmarking tools, reflecting a pragmatic approach to cross-layer performance tuning. Fluent in Python, C/C++, Scala/Java, he couples research-informed methods with production engineering to turn complex distributed systems into reliable, efficient ML platforms.
12 years of coding experience
8 years of employment as a software developer
Master of Science (MS), Computer Science, Master of Science (MS), Computer Science at Communication University of China
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (10)
docker10
bash10
dockers10
cicd10
xpu9
buildkite9
buildkit9
roc9
inference8
python7
Programming languages (8)
Github contributions (5)
vllm-project/vllm
Aug 2024 - Mar 2025
A high-throughput and memory-efficient inference and serving engine for LLMs
Role in this project:
DevOps Engineer
DevOps EngineerContributions:19 reviews, 13 PRs, 39 comments in 7 months
Contributions summary:Chendi primarily contributed to the CI/CD and testing infrastructure of the vLLM project. They developed and modified scripts (`run-hpu-test.sh`) to build Docker images and run offline inference, specifically targeting HPU (Habana Processing Unit) hardware. Furthermore, the user addressed issues related to the HPU device setup within the CI/CD pipeline, ensuring proper hardware visibility. Their work focused on enabling and validating inference capabilities on different hardware platforms, particularly HPU.
amdcudadeepseekgpthpu
oap-project/recdp
Jul 2021 - Sep 2022
Contributions:5 reviews, 75 commits, 9 PRs in 1 year 2 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.