Wenjie Du
Co-Founder & CTO at PyPOTS
Montreal, Quebec, Canada
Summary
🤩
Rockstar🎓
Top SchoolWenjie Du is a machine-learning researcher and engineering-led CTO with 10 years of experience specializing in modeling partially-observed and irregularly-sampled time series. As Co-Founder & CTO at SE.ai he designs LLM agent systems and architects full-stack AI platforms, while leading PyPOTS — an open-science ecosystem for POTS analysis that has amassed 2M+ downloads, 2K+ stars and 1K+ citations. His technical roots include SAITS and BRITS imputation work and building the PyPOTS toolkit (core dataset classes and imputer implementations), reflecting a focus on reproducible, reality-centric solutions that bridge research and production. Based in Montreal, he collaborates with academic and industry partners (King’s, Tsinghua, Ciena) to validate models on medical and infrastructure data, and he favors the Unix philosophy: do one thing and do it well. Notably, he combines deep research rigor with hands-on product engineering, making his open-source contributions directly usable in real-world AI systems.
10 years of coding experience
2 years of employment as a software developer
M.A.Sc., Electrical and Computer Engineering > Machine Learning, M.A.Sc., Electrical and Computer Engineering > Machine Learning at Concordia UniversityBachelor's degree, Software Engineering, Bachelor's degree, Software Engineering at China University of Petroleum 中国石油大学(华东)
Github Skills (9)
neural-network10
data-mining10
pytorch10
machine-learning10
time-series10
deep-learning10
python10
back-end-development10
data-analysis10
Programming languages (8)
Github contributions (5)
WenjieDu/PyPOTS
Mar 2022 - Jan 2023
A Python toolkit/library for reality-centric machine/deep learning and data mining on partially-observed time series, including SOTA neural network models for scientific analysis tasks of imputation/classification/clustering/forecasting/anomaly detection/cleaning on incomplete industrial (irregularly-sampled) multivariate TS with NaN missing values
Role in this project:
Back-end Developer
Back-end DeveloperContributions:41 releases, 11 reviews, 198 commits in 9 months
Contributions summary:Wenjie primarily contributed to setting up the project structure and implementing core features, including adding setup files and version control. They added the base dataset class. They implemented the BRITS imputer, a recurrent neural network-based model for time series imputation. The contributions focus on building the underlying infrastructure and core modules of the time-series analysis toolkit.
forecastingpythontime-series-analysismissing-valuesdata-mining
WenjieDu/WenjieDu
Apr 2022 - Mar 2023
Contributions:23 commits, 7 PRs, 87 pushes in 10 months
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.