Zheyu Ye
Machine Learning Engineer at Xiaohongshu
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolZheyu Ye is a Machine Learning Engineer based in Shanghai with seven years of experience building and productionizing NLP models across industry leaders including Xiaohongshu, Trip.com and AWS. He specializes in question answering and model integration, with hands-on work on BERT, MobileBERT and RoBERTa within the widely used Gluon-NLP framework—contributions that include dataset/script updates, Horovod training support, and refactoring for deployment. Trained at Imperial College London (MSc Advanced Computing) and Wuhan University of Technology, he blends academic rigor with practical engineering to move research into scalable systems. Known as an initiative-taking beginner and seeker in NLP, he brings a curious, implementation-focused approach to pushing state-of-the-art models into real products.
7 years of coding experience
2 years of employment as a software developer
Master of Science - MS, Advanced Computing, Master of Science - MS, Advanced Computing at Imperial College LondonBachelor of Engineering - BE, Computer Software Engineering, Bachelor of Engineering - BE, Computer Software Engineering at Wuhan University of Technology
Github Skills (17)
system-configuration10
python10
machine-learning10
gluon10
custom-configuration10
deeplearning-ai10
deep-learning10
question-answering10
bert10
roberta10
configurations10
nlp10
yml-configuration10
mxnet9
trainings9
Programming languages (8)
Github contributions (5)
dmlc/gluon-nlp
Feb 2020 - Sep 2020
NLP made easy
Role in this project:
ML Engineer
ML EngineerContributions:36 reviews, 12 commits, 16 PRs in 6 months
Contributions summary:Zheyu primarily contributed to improving and maintaining question answering models within the Gluon-NLP framework. Their work involved fixing configuration files for BERT, MobileBERT, and RoBERTa models, suggesting a focus on model integration and optimization. The user also updated and revised QA datasets and scripts, including implementing Horovod support, which indicates an involvement in model training and deployment. Furthermore, the user was involved in refactoring and converting model files.
nlpmxnetnatural-language-understandingnlgnatural-language-generation
zheyuye/zheyuye.github.io
Feb 2021 - Mar 2025
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Contributions:71 pushes, 1 branch in 4 years 2 months
templategithub-pages-templatemmistakesmistakesjekyll
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.