Rice University
New York University
Adam JermynMember of Technical Staff · AnthropicResearcher↗
Researcher
Ethan Perez
AnthropicResearch Scientist
Perez leads Anthropic's alignment team. He introduced automated red-teaming, which uses AI to find dangerous behavior before release, and led safeguards that make it harder to obtain harmful information from Claude. His work focuses on keeping increasingly capable systems honest and safe.
Career & education
Current roleAnthropicMay 2022-presentResearch Scientist
AnthropicMay 2022-presentPreviously
Google DeepMind2021-2021Research Scientist Intern
Meta2019-2020NLP Research Intern
Google DeepMind2021-2021Meta2019-2020Education
Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations49,791As of Jun 15, '26
citations+25,951Since last snapshot, Aug 25, '25
Selected contributions
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
With Patrick Lewis, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis and others ·RAG finds relevant documents to help a language model generate better-informed answers.
Constitutional AI: Harmlessness from AI Feedback
With Yuntao Bai, Saurav Kadavath, Sandipan Kundu, Amanda Askell, Jackson Kernion, Andy Jones, Anna Chen and others ·Trained AI assistants to critique and improve their answers using a written set of principles.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 22, 2026 · Checked for accuracy and new information.
