Eric Wallace
Member Of Technical Staff at OpenAI
San Francisco, California, United States
Summary
🤩
Rockstar🎓
Top SchoolEric Wallace is a machine learning researcher and software engineer with 11 years of experience, currently a Member of Technical Staff at OpenAI focused on making large language models more trustworthy, secure, robust, and private. He earned a PhD in Computer Science from UC Berkeley and brings deep NLP and ML-security expertise from research internships at DeepMind, Meta FAIR, and AI2. A proven contributor to prominent open-source tooling—most notably enhancements to AllenNLP’s interpretability module including HotFlip and SmoothGrad—he blends rigorous research with production-quality engineering and test-driven improvements. Based in San Francisco, he has a track record of translating cutting-edge interpretability and robustness ideas into usable tools and evaluative code, and maintains a public research portfolio at ericswallace.com.
11 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of California, BerkeleyBachelor of Science (B.S.) Computer Engineering, Bachelor of Science (B.S.) Computer Engineering at University of Maryland
Spanish, English
Github Skills (8)
pytorch10
machine-learning10
nlp10
python10
natural-language-processing10
data-science10
allennlp10
testing9
Programming languages (7)
Github contributions (5)
allenai/allennlp
Jul 2019 - Oct 2019
An open-source NLP research library, built on PyTorch.
Role in this project:
ML Engineer
ML EngineerContributions:8 commits, 10 PRs, 11 pushes in 2 months
Contributions summary:Eric made significant contributions to the AllenNLP library, focusing on the `interpret` module. They implemented and improved interpretability features, specifically for the HotFlip and SmoothGrad attackers. The user also addressed bug fixes, refactored existing code, and added test cases to enhance the module's functionality and robustness. Furthermore, they updated the Sentence Tagger predictor for the interpret UI.
nlppytorchtransformerspythonbert
Eric-Wallace/interpretability-tutorial-emnlp2020
Aug 2020 - Dec 2020
Contributions:23 commits, 22 pushes, 1 branch in 3 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.