- Role
- Alignment research lead
- Joined Anthropic
- 2022
- Before Anthropic
- Straight from university
Career
- Anthropic
- Alignment team lead2024 – present
- Research Scientist; led the adversarial robustness team2022
Education
- PhD, Natural Language Processing/Computer Science, New York University
- Bachelor's, Rice University (Engineering department's Outstanding Senior)
Sources1far.ai
Lesser-known facts
- Considered quitting an internship to start a robotics company with a friend.
- Won a best paper award at ICML 2024 and made Forbes 30 Under 30 in AI.
- Discovered the career group 80,000 Hours as a computer science undergraduate, then interned at Mila in Quebec.
- Attended a Machine Intelligence Research Institute workshop on AI safety in 2017, while still at Rice.
- Interned at Uber on fraud detection through a KPCB Fellowship and at Google Maps on localization algorithms.
- Founded and coached a MathCounts program at St. Mark's Catholic School in 2012.
- Wrote his NYU PhD thesis on fixing undesirable behavior in language models.
- Led the team behind Constitutional Classifiers, which let Anthropic deploy Claude Opus 4 despite its ability to assist advanced weapons development.
Known for
- Retrieval-Augmented Generation (RAG, 2020)
- Automated Red Teaming (2022)
- Constitutional Classifiers
- Sleeper Agents (2024)
- Measuring faithfulness in chain-of-thought reasoning (2023)
- Question Decomposition Improves the Faithfulness of Model-Generated Reasoning (2023)
Sources1ethanperez.net
Honors
Best paper award at ICML 2024 · Forbes 30 Under 30 in AI (2025) · Rice University Engineering department's Outstanding Senior
Sources1ethanperez.net
