Jjune Oxen
Summary
🤩
RockstarJason Cho is a software engineer with nine years of experience building automation, CI/CD pipelines, and ML model tooling across enterprises like Meta, Capital One, and IBM. He combines strong systems and programming skills in Java, C, Python, Linux and JavaScript with hands-on experience in Jenkins, Ansible, and cloud-native deployments. Currently contributing to Captum at Meta, he has enhanced PyTorch model interpretability features—improving attribution methods, GPU support for LLM attribution, and test coverage—bringing practical ML engineering into open source. A Boston University CS graduate with a Master’s in Machine Learning from Georgia Tech, he blends academic rigor with a history of organizing and mentoring in campus hackathon and CS support roles. Based in New Jersey, he’s notable for translating research-grade ML interpretability work into production-ready tooling.
9 years of coding experience
Github Skills (9)
pytorch10
machine-learning10
interpretation10
python10
feature-selection9
testing9
nlp4
computer-vision4
natural-language-processing4
Programming languages (6)
Github contributions (5)
meta-pytorch/captum
Jun 2024 - Sep 2025
Model interpretability and understanding for PyTorch
Role in this project:
ML Engineer
ML EngineerContributions:8 reviews, 16 PRs, 36 pushes in 1 year 3 months
Contributions summary:Jjune primarily contributed to the interpretability and understanding of PyTorch models within the captum repository. Their work focused on adding functionality to various attribution methods, including LayerGradCam, InternalInfluence, and others, enabling the passing of `grad_kwargs` for more flexible gradient calculations. They also addressed GPU support issues for LLM attribution models and enhanced test coverage with the use of PyTorch futures, particularly within feature permutation implementations. The user demonstrates proficiency in expanding and refining core captum attribution functionalities.
pytorchinterpretabilityinterpretable-aiinterpretable-mlfeature-importance
j-t-1/captum
Mar 2025 - May 2025
Model interpretability and understanding for PyTorch
Contributions:16 pushes in 2 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.