Sihan Chen
Machine Learning Engineer at Intel Corporation
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolSihan Chen is a Machine Learning Engineer with eight years of software and systems experience, currently working at Intel and pursuing an MS in Software Engineering of Distributed Systems at KTH. He blends practical ML model optimization—contributing to Intel's widely used neural-compressor project for low-bit LLM quantization—with backend and DevOps work, improving cross-platform stability in the EMQX MQTT broker. His background spans end-to-end AI systems from a video-based fire detection bachelor project to a KTH master thesis building a temporal graph library on Flink Stateful Functions for streaming graph algorithms. Comfortable across Python, TensorFlow/PyTorch, Erlang-based systems and production benchmarks, he focuses on making ML models and distributed services both efficient and robust. Based in Shanghai, he brings a pragmatic engineering mindset that connects research-grade model compression to real-world deployment challenges.
7 years of coding experience
Master of Science - MS, Software Engineering of Distributed System, Master of Science - MS, Software Engineering of Distributed System at KTH Royal Institute of TechnologyBachelor of Science - BS, Information Technology, 1.8/1.0, Bachelor of Science - BS, Information Technology, 1.8/1.0 at Technische Hochschule LübeckBachelor of Engineering - BE, Electrical Engineering and Automation, 3.7/4.0, Bachelor of Engineering - BE, Electrical Engineering and Automation, 3.7/4.0 at East China University of Science and Technology
Github Skills (21)
pytorch10
benchmark10
brokers10
erlang10
python10
windows10
mqtt10
configuration-management10
machine-learning10
broker10
benchmarking10
mqttnet10
tensorflow10
message-broker10
quantization10
Programming languages (10)
Github contributions (5)
intel/neural-compressor
Oct 2022 - Jan 2023
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
Role in this project:
ML Engineer
ML EngineerContributions:26 reviews, 62 commits, 35 PRs in 3 months
Contributions summary:Sihan primarily contributed to the `neural-compressor` repository, focusing on the benchmarking and quantization aspects of machine learning models. They added features to support multi-instance benchmarking, improved the benchmark class, and fixed related bugs. The commits also included code refinements and updates to example scripts, particularly for object detection tasks, demonstrating a focus on model optimization and integration within the framework.
knowledge-distillationauto-tuningcompressorsparsityintel
emqx/emqx
Aug 2021 - Dec 2021
The most scalable open-source MQTT broker for IoT, IIoT, and connected vehicles
Role in this project:Back-end Developer & DevOps Engineer
Back-end Developer & DevOps EngineerContributions:1 review, 15 commits, 15 PRs in 3 months
Contributions summary:Sihan primarily focused on improving the compatibility and stability of the EMQX broker. They addressed Windows-related compilation issues within the Erlang-based project, modifying the build process and configuration. Furthermore, they contributed to structured logging improvements across various modules and fixed a starting error related to paths with spaces. These changes highlight a focus on cross-platform support and operational improvements.
mqtt-servertelecomconnectedlwm2mmqtt-broker
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.