Shilin He
Applied Scientist at ByteDance
Beijing, China
Summary
🤩
Rockstar🎓
Top SchoolShilin He is an applied scientist with a decade of experience building and researching large language models and AI-driven developer tools, currently developing AI coding models at ByteDance Douyin. Previously at Microsoft he advanced LLM applications such as RAG, agents and TaskWeaver, contributing to production-facing systems like CloudGPT and UFO. His PhD in Computer Science from CUHK underpins a strong research-to-product track record spanning model fine-tuning, SFT, RL, and retrieval-augmented workflows. He also has hands-on systems experience from early contributions to the widely used loglizer toolkit, where he improved log clustering and anomaly detection pipelines. Based in Beijing, he combines deep academic training with practical engineering delivery across AI for software engineering and large-scale ML services.
10 years of coding experience
4 years of employment as a software developer
Bachelor of Technology - BTech, Computer Science, Bachelor of Technology - BTech, Computer Science at South China University of TechnologyThe Chinese University of Hong Kong (CUHK)
Github Skills (9)
scipy10
machine-learning10
anomaly-detection10
python10
log-analysis10
numpy10
data-processing9
algorithms8
clustering-algorithm8
Programming languages (3)
Github contributions (5)
logpai/loglizer
May 2016 - Jan 2020
A machine learning toolkit for log-based anomaly detection [ISSRE'16]
Role in this project:
Back-end Developer
Back-end DeveloperContributions:67 commits, 2 PRs, 62 pushes in 3 years 8 months
Contributions summary:Shilin contributed to the core logic of the log analysis toolkit, specifically within the `LogClustering` module. Their commits focused on implementing and updating code related to time windowing, data processing, and anomaly detection algorithms. The changes involved modifications to data loading, weighting, and clustering methods using libraries like NumPy and SciPy, improving the functionality of the log analysis tool. The contributions also show work related to BGL data, indicating specific use-case focus.
anomalyanalysis-toolkitlog-analysisanomaly-detectionmachine-learning
ShilinHe/interpretableNLP
Jul 2019 - Dec 2020
A list of publications on NLP interpretability (Welcome PR)
Contributions:8 commits, 3 pushes in 1 year 5 months
nlpinterpretabilitybertwelcomenatural-language-processing
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.