Kyunggeun Lee
Staff Engineer at Qualcomm
San Diego, California, United States
Summary
🤩
Rockstar🎓
Top SchoolKyunggeun Lee is a Staff Engineer based in San Diego with four years of experience building production-grade software at Qualcomm, progressing from Software Engineer to Staff Engineer in a few years. He combines strong hands-on systems engineering with practical ML model optimization skills, notably contributing PyTorch AutoQuant and testing tooling to the AIMET library for neural network quantization. His academic foundation from Seoul National University (BS and MS in Computer Science and Engineering) complements his applied work on model compression and post-training quantization techniques. Known for moving research-grade tools toward production readiness, he focuses on pragmatic implementations that improve inference efficiency on edge hardware. Colleagues describe him as a fast learner who scales technical contributions across both firmware-level and ML tooling domains. He often bridges firmware constraints and ML accuracy tradeoffs, making him effective at optimizing models for real-world devices.
4 years of coding experience
4 years of employment as a software developer
Seoul National University
Github Skills (7)
quantization10
pytorch10
quants10
machine-learning10
deep-learning10
model-optimization10
tensorflow8
Programming languages (1)
Github contributions (3)
quic/aimet
Oct 2021 - Jan 2023
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Role in this project:
ML Engineer
ML EngineerContributions:152 reviews, 62 commits, 825 PRs in 1 year 2 months
Contributions summary:Kyunggeun Lee's contributions primarily focused on enhancing the AIMET library for model quantization and compression. Their work included implementing and integrating various post-training quantization techniques, such as AutoQuant, and optimizing existing features. Significant contributions involved the implementation of PyTorch AutoQuant, alongside the creation of a testing tool and a user guide for this feature, demonstrating expertise in model optimization within the PyTorch framework.
pytorchtechniquesdeep-learningpruningcompression
quic-kyunggeu/aimet
Nov 2021 - Apr 2025
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Contributions:113 pushes, 835 branches in 3 years 5 months
pytorchtechniquesdeep-learningpruningcompression
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.