Gabriel Orlanski
Graduate Research Assistant
Madison, Wisconsin, United States
Summary
👤
Senior🎓
Top SchoolGabriel Orlanski is a PhD candidate and graduate research assistant at the University of Wisconsin–Madison with a decade of experience in ML and NLP research and engineering. He has interned and contributed to research teams at Google, Replit, Magic, X, and Merlin Labs, working on code generation, program synthesis, semantic parsing, and production-ready model pipelines. A hands-on contributor to open-source ML security tooling, he implemented and debugged a PyTorch adversarial attack in the widely used Adversarial Robustness Toolbox. Gabriel blends rigorous academic work with practical engineering—building experiment tracking for 1,200+ runs, shipping NLP models that improved baselines by multiple factors, and even applying ML to entrepreneurial ventures that generated meaningful revenue. Based in Madison, he pairs deep research instincts with applied systems know-how, often surfacing simple engineering fixes that unlock complex experiments.
10 years of coding experience
3 years of employment as a software developer
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at University of Wisconsin-MadisonMaster of Science - MS Computer Science, Master of Science - MS Computer Science at New York UniversityHigh School, High School at Columbia Grammar and Preparatory SchoolBachelor's degree Computer Science, Bachelor's degree Computer Science at Rensselaer Polytechnic Institute
Github Skills (7)
pytorch10
machine-learning10
adversarial-attacks10
python10
tensorflow9
ai9
tensor9
Programming languages (5)
Github contributions (5)
Trusted-AI/adversarial-robustness-toolbox
May 2021 - May 2021
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:11 commits, 3 PRs, 1 comment in 6 days
Contributions summary:Gabriel contributed significantly to the `OverTheAirFlickeringTorch` attack within the Adversarial Robustness Toolbox, primarily focusing on its implementation in PyTorch. Their work involved modifying the attack parameters, addressing delta shape issues, and fixing related code errors. They also worked on adapting the existing code to integrate seamlessly with the ART framework, adding tests and making adjustments for correct functionality.
extractionpythonfairness-mlrobustnessadversarial-machine-learning
gabeorlanski/bimodal-code-generation
Jan 2022 - May 2022
Contributions:1212 commits, 173 pushes in 4 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.