Dihao Chen
Senior Software Engineer at S.F. EXPRESS CO. LTD
Shenzhen, Guangdong Province, China
Summary
🤩
Rockstar🎓
Top SchoolDihao Chen is a Senior Software Engineer with 13 years' experience building distributed storage, cloud and ML infrastructure, currently driving AI platform and LLM infrastructure at S.F. Express from Shenzhen. He combines deep systems expertise (HBase, Ceph, OpenStack) with hands-on ML/Deep Learning engineering using TensorFlow and Kubernetes, having led Xiaomi’s first unified cloud platform for deep learning. As author of the popular Seagull container UI and contributor to projects like TVM and OpenMLDB, he bridges full-stack development, MLOps and compiler integration for production-grade model serving. Notably, his TensorFlow template and serving projects demonstrate end-to-end ML deployment skills—from model training and inference to Django-based production services and hyperparameter tuning infrastructure.
12 years of coding experience
7 years of employment as a software developer
学士, Software engineering, Top, 学士, Software engineering, Top at 华南理工大学
English, Chinese, Chinese, teochew
Github Skills (47)
tvm10
docker10
back-end-development10
python10
django10
modeler10
machine-learning10
inference10
webpages10
modello10
dockers10
flask-ask10
mask-rcnn10
go10
deep-learning10
Programming languages (18)
Github contributions (5)
tobegit3hub/simple_tensorflow_serving
Jan 2018 - Nov 2020
Generic and easy-to-use serving service for machine learning models
Role in this project:
Back-end & DevOps Engineer
Back-end & DevOps EngineerContributions:253 commits, 14 PRs, 173 pushes in 2 years 10 months
Contributions summary:Dihao's contributions focused on establishing the core functionality of a serving service for machine learning models. They implemented the initial HTTP server using Flask to handle incoming requests and interact with TensorFlow models. The user also implemented server configuration and model versioning, and introduced the use of Python libraries such as `requests` for testing and `base64` for encoding binary files. Finally, the user integrated and configured uwsgi web server and created shell scripts for both the build and deployment.
pythonservingmxnetdata-sciencemachine-learning
tobegit3hub/tensorflow_template_application
Jul 2016 - May 2021
TensorFlow template application for deep learning
Role in this project:ML Engineer
ML EngineerContributions:195 commits, 10 PRs, 166 pushes in 4 years 10 months
Contributions summary:Dihao implemented a deep learning model within a TensorFlow template application for deep learning. The user added the initial data and model, which was then improved with added scalar summaries, model checkpointing, and inference capabilities. The user implemented an inference mode using test data and expanded it with a Django-based cancer prediction service, demonstrating full-stack ML model deployment.
csvmlpservinglibsvmdeep-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.