Been Kim

Research Scientist at Google DeepMind

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
Been Kim is a research-focused engineering leader with 11+ years driving human-centered interpretability at Google Brain and DeepMind, now serving as Director. She bridges rigorous ML research and practical tooling—most notably as a lead on the influential TCAV interpretability project (featured at Google I/O and honored by UNESCO)—and has shaped the field through keynotes at ICLR, ECML and the G20. An MIT PhD, she pairs academic depth with product-minded engineering, contributing code, compatibility fixes and visualization improvements to open-source TCAV. Beyond building tools, she studies how machine representations compare to human concepts and advocates for higher-level, human-friendly model languages. Active in shaping the community, she has held senior program and committee roles across NeurIPS, ICLR, ICML and FAccT and helped organize long-running workshops on human interpretability.
code11 years of coding experience
github-logo-circle

Github Skills (11)

model-building10
machine-learning10
interpretation10
tensorflow10
python10
modeling10
model-driven10
model-driven-development10
scikit-learn9
scikit9
computer-vision8

Programming languages (5)

C++TeXJupyter NotebookTerraPython

Github contributions (5)

github-logo-circle
tensorflow/tcav

Aug 2018 - Sep 2021

Code for the TCAV ML interpretability project
Role in this project:
userML Engineer
Contributions:35 commits, 17 PRs, 40 pushes in 3 years 1 month
Contributions summary:Been primarily contributed to the `tcav` repository, a project focused on the TCAV ML interpretability method. Their commits demonstrate expertise in model-related aspects by modifying the image value range for an InceptionV3 model and addressing warnings related to model training. The user also implemented changes to the plotting utilities and added arguments to address deprecation warnings from sklearn. Moreover, they modified the code by adding comments and fixing an issue with Python 3 compatibility.
machine-learninginterpretabilitytcav
BeenKim/MMD-critic

Sep 2017 - Jun 2019

Contributions:11 commits, 9 PRs, 11 pushes in 1 year 9 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