Jeongmin Lee

Research Scientist

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

👤
Senior
Jeongmin Lee is a Senior Research Scientist based in the San Francisco Bay Area with a decade of experience building internet-scale personalization and ranking systems at Meta and Instagram. He specializes in sequence models and user history modeling for feeds and Reels, translating cutting-edge research into production recommender systems. His work spans research, engineering and open-source contributions—he was a core developer and notebook contributor to NVIDIA's widely used Transformers4Rec library, demonstrating PySpark/PetaStorm data pipelines and transformer-based training techniques. Jeongmin holds a PhD in Computer Science from the University of Pittsburgh and brings a history of applied ML across industry internships and impactful volunteer software projects in global health.
code10 years of coding experience
github-logo-circle

Github Skills (13)

data-preprocessing10
huggingface-transformers10
pytorch10
transformer10
pyspark10
machine-learning10
recommender-system10
natural-language-processing9
tabular9
data-engineering9
datatable9
nlp9
bert8

Programming languages (7)

JavaC++ScalaHTMLSwiftRubyPython

Github contributions (5)

github-logo-circle
Transformers4Rec is a flexible and efficient library for sequential and session-based recommendation and works with PyTorch.
Role in this project:
userData Scientist & ML Engineer
Contributions:146 commits in 3 months
Contributions summary:Jeongmin contributed a notebook demonstrating PySpark-based data preprocessing, data loading with PetaStorm, and the implementation of a Hugging Face transformer model. The work included loading and processing e-commerce data, converting timestamps, and performing feature engineering. They also updated a runner file for the transformer model and implemented a negative sampling approach for model training.
pytorchtransformertabular-datahuggingfacebert
leej35/leej35.github.io

Jun 2016 - Mar 2026

Contributions:108 pushes in 9 years 11 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.
Request Free Trial