Henry Eigen
SDE II at Amazon Web Services (AWS)
New York, New York, United States
Summary
👤
Senior🎓
Top SchoolHenry Eigen is an SDE II at AWS in New York with nine years of engineering experience and a BS in Computer Science from the University of Tennessee, Knoxville. He focuses on secure access control systems for AWS data centers, automating customer pain points and liaising on research with Johns Hopkins. His background blends academic research in adversarial defenses and computer vision with practical ML engineering—he contributed to the widely used Adversarial Robustness Toolbox by improving ProjectedGradientDescent initialization for adversarial training. Henry has taught probability courses and built high-performance RL policy implementations during research stints, reflecting a mix of rigorous theory and production-minded coding. Colleagues describe him as someone who moves smoothly between research prototypes and hardened, secure systems.
8 years of coding experience
3 years of employment as a software developer
Bachelor of Science - BS, Computer Science, Bachelor of Science - BS, Computer Science at University of Tennessee, Knoxville
Github Skills (7)
machine-learning10
adversarial-machine-learning10
adversarial-attacks10
python10
numpy10
eval8
scipy8
Programming languages (5)
Github contributions (5)
Trusted-AI/adversarial-robustness-toolbox
Jan 2020 - Jan 2020
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
Role in this project:
ML Engineer
ML EngineerContributions:6 commits, 3 PRs, 2 comments in 11 days
Contributions summary:Henry's contributions center on modifying the `ProjectedGradientDescent` attack within the Adversarial Robustness Toolbox. They added the functionality to randomly initialize epsilon within a truncated normal distribution, which is a technique used in adversarial training. The user also made code style changes and improved comments related to the `random_eps` parameter and related attack methodology. They are working with the core functionality of the framework, modifying and refining its behavior.
extractionpythonfairness-mlrobustnessadversarial-machine-learning
CS340-21/EasyRec
Feb 2021 - Apr 2021
Contributions:31 PRs, 54 pushes, 2 branches 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.