lxww301 

Beijing, China
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

🤩
Rockstar
Weiwei Xu is a research-focused software engineer with nine years of experience at the intersection of NLP, ML deployment, and software compliance. As a Graduate Research Assistant at Peking University and incoming visiting Ph.D. student at UC Davis, Weiwei built LicenseRec, an end-to-end system for automated open-source license compliance, and created LiCoEval, the first benchmark evaluating LLMs on license-aware code generation—work published at ASE’23 and ICSE’25. Hands-on MLOps contributions include optimizing multi-GPU inference, concurrency, and Redis-backed serving for BERT in the service-streamer project, reflecting a strong practical bent for taking models to production. Based in Davis, CA and self-described as “yet another NLPer,” Weiwei combines deep academic rigor with pragmatic engineering to tackle legal and operational gaps in modern code-generation tooling.
code9 years of coding experience
github-logo-circle

Github Skills (19)

continuous-deployment10
pytorch10
python10
multithreading10
python-multiprocessing10
ml-deployment10
deep-learning10
thread10
hyper-threading10
multiprocessing10
multi-process10
threaded10
redis9
web-content9
webpages9

Programming languages (2)

Jupyter NotebookPython

Github contributions (5)

github-logo-circle
ShannonAI/service-streamer

Jul 2019 - Nov 2019

Boosting your Web Services of Deep Learning Applications.
Role in this project:
userMLOps Engineer
Contributions:27 commits, 19 PRs, 7 pushes in 3 months
Contributions summary:Lxww301 primarily focused on enhancing the service-streamer library for deploying and serving deep learning models. Their contributions included adding support for multi-GPU inference using multiprocessing and threading, integrating logging for monitoring, and refactoring code to improve performance. Further improvements involved optimizing the service for handling multiple concurrent requests via a future API and integrating with a Redis broker. The user’s work centered around the deployment and optimization of a BERT model.
deep-learningwebservicepytorchmodel-deploymenttensorflow
pku-wuwei/LatticeLSTM

Jan 2019 - Jan 2019

Chinese NER using Lattice LSTM. Code for ACL 2018 paper.
Contributions:37 commits, 6 PRs, 23 pushes in 6 days
lstm
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.
Request Free Trial