Dan Liang
Video Software Engineer at Intel Corporation
China
Summary
👤
Senior🎓
Top SchoolDan Liang is a Video Software Engineer at Intel with 14 years of embedded systems experience, specializing in board support packages and low-level OS work across Linux, .NET Micro Framework and VxWorks. He has a strong track record in embedded video and platform software from roles at Intel, Atmel and SonicWALL, blending firmware, drivers and OS integration. Recently he has applied model optimization skills to ML inference work—contributing TensorFlow model tuning and benchmarking to Intel's neural-compressor project—showing a practical bridge between embedded systems and efficient AI inference. Based in China and grounded in deep low-level expertise, he brings a pragmatic focus on performance, portability and production-ready tooling.
14 years of coding experience
4 years of employment as a software developer
East China Normal University
Github Skills (9)
auto-tuning10
quantization10
benchmark10
benchmarking10
tensorflow10
python10
model-compression10
large-language-models9
post-training9
Programming languages (4)
Github contributions (5)
intel/neural-compressor
Aug 2020 - Sep 2020
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:6 commits in 28 days
Contributions summary:Dan's commits focus on optimizing and evaluating TensorFlow models for the `intel/neural-compressor` repository, a project centered on low-bit quantization and model compression. They enabled and configured a specific model, "Wide_and_Deep," integrating it into the inference pipeline. The contributions demonstrate experience with model optimization techniques and the use of the `intel/neural-compressor` framework for benchmarking and tuning model performance. The user also refined the benchmarking scripts and configuration, showing a focus on practical application.
knowledge-distillationauto-tuningcompressorsparsityintel
dliang0406/dldt
Oct 2018 - Oct 2019
Deep Learning Deployment Toolkit
Contributions:5 commits, 4 PRs, 4 pushes in 11 months
pythoncaffe2deep-learningdeploymentmachine-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.