Liangfu Chen
Senior Software Dev Engineer at Amazon Web Services (AWS)
California, United States
Summary
🤩
Rockstar🎓
Top SchoolLiangfu Chen is a Senior Software Development Engineer with 14 years of experience building ML systems, compilers, and production inference stacks at AWS and previously HARMAN and research institutes. His work bridges deep learning research—CNNs, attention models, 3D reconstruction and topology-aware vision—with pragmatic engineering, contributing to high-profile open-source projects like MMdnn, TVM and vLLM to improve model interoperability, compilation and high-throughput LLM serving. At AWS he has focused on productionizing model backends (including AWS Neuron support) and optimizing ONNX/ONNX Runtime workflows for faster inference. Liangfu’s strengths include low-level compiler and GPU-accelerated computation plus practical MLOps for CI/CD and dockerized deployments. He holds an MEng in Computer Science & Engineering and brings a cross-disciplinary background spanning biology and pharmaceutical engineering, which informs his systems-oriented curiosity and attention to complex, multi-modal problems. Colleagues describe him as a researcher-engineer who reliably translates cutting-edge ML ideas into robust, deployable infrastructure.
14 years of coding experience
12 years of employment as a software developer
Bachelor of Science (BS), Biology, Bachelor of Science (BS), Biology at Nanjing Xiaozhuang CollegeMaster of Engineering (MEng), Computer Science & Engineering, Master of Engineering (MEng), Computer Science & Engineering at Chung-Ang UniversityBachelor of Science (BS), Pharmaceutical Engineering, Bachelor of Science (BS), Pharmaceutical Engineering at Woosuk University
Chinese, English, Korean
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (37)
pytorch10
compilation10
python10
scikit10
mxnet10
machine-learning10
inference10
onnx10
datatable10
cicd10
datatables10
deeplearning-ai10
compiler-compiler10
mlops10
deep-learning10
Programming languages (15)
Github contributions (5)
vllm-project/vllm
Nov 2023 - Apr 2025
A high-throughput and memory-efficient inference and serving engine for LLMs
Role in this project:
MLOps Engineer
MLOps EngineerContributions:132 reviews, 20 PRs, 152 comments in 1 year 4 months
Contributions summary:Liangfu's contributions primarily center around integrating and supporting the AWS Neuron backend for vLLM, an inference and serving engine for LLMs. They added features to build with Neuron, implemented support for transformers-neuronx, and added documentation. The user also implemented and updated CI/CD scripts with docker images and optimized test configurations for the Neuron backend to improve model serving capabilities.
amdcudadeepseekgpthpu
autogluon/autogluon
Oct 2022 - Jan 2023
Fast and Accurate ML in 3 Lines of Code
Role in this project:ML Engineer
ML EngineerContributions:176 reviews, 16 commits, 60 PRs in 2 months
Contributions summary:Liangfu's contributions center on enhancing the capabilities of the AutoGluon library within the context of tabular data and ONNX runtime. They implemented support for random forest model prediction using the ONNX runtime, including compiling models for faster inference and integrating the ONNX compiler within the RFModel. Additionally, they introduced a compilation function to the tabular predictor. The user also updated onnx and skl2onnx versions to the latest. Furthermore, they worked on fixing an issue with tabular NN onnx conversion for Windows.
forecastingimage-textmlppythonmeta-learning
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.