Haebin Shin
Research Intern at Microsoft
Seoul, South Korea
Summary
👤
Senior🎓
Top SchoolHaebin Shin is an NLP-focused research engineer with 10 years of experience building and compressing large language models and deploying applied AI systems across industry. Currently a research intern at Microsoft and advised by Minjoon Seo at KAIST, he has contributed to efficient LLM techniques such as context distillation and vocabulary-agnostic knowledge distillation for pretraining. At Samsung Research he helped develop billion-parameter foundation models for Galaxy AI, built code-intelligence tooling, and published on hierarchical semantic retrieval for low-resource devices. Earlier work at ESTsoft produced deployed semantic retrieval and malware-detection systems, showing a strong track record of turning research into production. He also contributed cross-platform installation automation to the popular konlpy Korean NLP project, reflecting attention to reproducibility and tooling.
10 years of coding experience
8 years of employment as a software developer
Bachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at Sogang UniversityMaster of Science - MS, Artificial Intelligence, Master of Science - MS, Artificial Intelligence at 한국과학기술원(KAIST)
Github Skills (8)
bash10
devops10
scripting10
automake10
python9
linux9
nlp5
text-mining4
Programming languages (4)
Github contributions (5)
konlpy/konlpy
Aug 2017 - Oct 2019
Python package for Korean natural language processing.
Role in this project:
DevOps Engineer
DevOps EngineerContributions:5 commits, 2 PRs, 1 comment in 2 years 1 month
Contributions summary:Haebin focused on scripting and automating the installation process for the MeCab library and its dependencies within the konlpy project. They updated the installation script (`mecab.sh`) to support different Linux distributions and corrected potential errors, especially around `apt-get` usage, including handling dependencies like automake. The user's contributions involved installing and configuring external dependencies, and ensuring MeCab could be installed successfully across different platforms.
nlppythonmorphologylanguage-processingnatural-language
HaebinShin/grad-cam-text
Apr 2018 - Nov 2020
Contributions:4 commits, 3 pushes, 1 branch in 2 years 8 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.