Xuehui Lin
Software Developer at Microsoft
Beijing, Finland
Summary
🤩
RockstarXuehui Lin is a seasoned software developer with 11 years of experience, currently at Microsoft in Beijing with a background at Nokia. She focuses on backend systems and ML tooling, contributing to high-profile open-source projects like Microsoft’s NNI (AutoML) and LightGBM, where she worked on hyperparameter tuning, Auto-GBDT features, and core gradient-boosting fixes. Comfortable navigating both algorithmic code and production-grade C++/Python backends, she blends practical bug fixes with feature work that improves model automation and reliability. Based in Finland and Beijing, she brings a cross-cultural perspective to global engineering teams and a habit of improving developer-facing tooling that quietly raises project quality.
11 years of coding experience
Github Skills (21)
c-language10
python10
machine-learning10
gradient-boosting10
hyperparameter-optimization10
decision-tree10
automated-machine-learning10
cprogramming-language10
gbm9
lightgbm9
deep-learning9
automl9
neural-architecture-search8
data-mining8
pytorch7
Programming languages (7)
Github contributions (5)
microsoft/nni
Sep 2018 - Apr 2020
An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
Role in this project:
ML Engineer
ML EngineerContributions:2 releases, 1 review, 74 commits in 1 year 7 months
Contributions summary:Xuehui primarily contributed to the `hyperopt_tuner.py` file, updating and refactoring code related to search space transformations within the Hyperopt tuning algorithm. Further contributions included the addition of basic features related to auto-gbdt, demonstrating involvement in automating hyperparameter tuning for gradient boosting decision trees, a core focus of the repository. The user also addressed minor coding style issues and bug fixes.
pythonneural-architecture-searchengineeringtensorflowbayesian-optimization
microsoft/LightGBM
Oct 2016 - Oct 2016
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
Role in this project:Back-end Developer
Back-end DeveloperContributions:16 commits, 7 PRs, 9 pushes in 11 days
Contributions summary:Xuehui primarily contributed to the back-end code, focusing on bug fixes and typo corrections within the LightGBM framework. Their work involved modifying source files related to gradient boosting algorithms, dataset handling, and tree learning. They also addressed minor documentation and configuration issues. These changes demonstrate a focus on maintaining and improving the core functionality of the gradient boosting library.
kagglepythondata-mininglightgbmmicrosoft
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.