Artificial intelligence
10 Anthropic AI safety researchers
These ten current Anthropic AI safety researchers hold research and Member of Technical Staff roles at the company that involve alignment, interpretability or safety work. A reader can learn what AI safety research work at Anthropic involves from people who have done it.
Professionals to explore
01—10Ajay Garg
LinkedInExperience: Research Scientist, Interpretability · Anthropic
Research Scientist, Interpretability at Anthropic since May 2024, based in the Los Angeles area. Before Anthropic they were a Staff machine learning Engineer at a stealth company (2023–2024), a Senior Machine Learning Engineer (2022–2023) and Senior Applied Scientist - Machine Learning (2021–2022) at Amazon, and a Machine Learning Engineer - NLP at Apple (2018–2021).
Alex Rodrigues
LinkedInExperience: AI Alignment Research · Anthropic
AI Alignment Research at Anthropic since October 2024, with the headline AI Alignment Research @ Anthropic. Before Anthropic they were Co-Founder and CEO of Embark Trucks, later acquired by Applied Intuition (2015–2023), and were a Thiel Fellow and part of the Y Combinator W16 batch.
Amanda Askell
LinkedInExperience: Member Of Technical Staff · Anthropic
Member Of Technical Staff at Anthropic since March 2021. The profile says they work on aligning and evaluating AI systems with a focus on large language models, have worked on AI policy and ethics, and have a background in formal ethics and decision theory. Before Anthropic they were a Research Scientist (Policy) at OpenAI (2018–2021).
Daniel Ziegler
LinkedInExperience: Member of Technical Staff · Anthropic
Member of Technical Staff at Anthropic since June 2024, based in San Francisco; the role description mentions Alignment Stress-Testing. Before joining they were a Member of Technical Staff at METR (2023–2024), a Member Of Technical Staff at Redwood Research (2021–2023) and a Member Of Technical Staff at OpenAI (2018–2021).
Euan Ong
LinkedInExperience: Member of Technical Staff (Alignment Science, Interpretability) · Anthropic
Member of Technical Staff (Alignment Science, Interpretability) at Anthropic since August 2024, based in San Francisco. Before Anthropic they were a Research Assistant at the University of Cambridge (2023–2024), a research intern at the Center for Human-Compatible AI and a software engineering intern at Jane Street.
Evan Hubinger
LinkedInExperience: Member of Technical Staff, Manager · Anthropic
Member of Technical Staff, Manager at Anthropic since January 2023. The profile describes them as Alignment Science org lead at Anthropic focused on red-teaming Anthropic's alignment, and the role description says they lead the Alignment Stress-Testing team. Earlier they were a Member of Technical Staff (Intern) at OpenAI in 2019.
Harrison Lee
LinkedInExperience: Member of Technical Staff · Anthropic
Member of Technical Staff at Anthropic since March 2026, based in the United Kingdom, with the headline Alignment researcher. Before joining they were a Staff Research Scientist at Google DeepMind from 2020 to 2026 and a Machine Learning Engineer at Facebook (2017–2020), after earlier consulting roles.
Joshua Batson
LinkedInExperience: Research Scientist · Anthropic
Research Scientist at Anthropic since March 2023; the role description says they study how neural nets work inside and what that means for performance and safety. Before Anthropic they were Chief Data Scientist at PHC Global (2021), a Senior Research Scientist at Biohub (2017–2021) and a machine learning consultant at Sift Security.
Liang Qiu
LinkedInExperience: Member of Technical Staff · Anthropic
Member of Technical Staff at Anthropic since February 2026; the profile says they work on scalable oversight at Anthropic and received a Ph.D. from UCLA. Before joining they were a Senior Applied Scientist (2024–2025) and Applied Scientist (2022–2024) at Amazon, and a research intern at Salesforce and Microsoft in 2021.
Sara Price
LinkedInExperience: Member of Technical Staff · Anthropic
Member of Technical Staff at Anthropic since January 2025, with the headline AI Safety and Alignment Researcher, after working as an Independent AI Alignment Researcher with Anthropic from August 2024. Earlier they were a Research Scholar at MATS Research (2023–2024), a Data Scientist at Bitquery and co-founded BlockRank.
Choose the right perspective
Match the person's research area to your question, since alignment stress-testing, interpretability, scalable oversight and model evaluation use different methods. Look at their path into safety work, from Google DeepMind, OpenAI and Redwood Research to startups and academia, because that shapes how they describe safety research inside a frontier lab.
Questions to take into the conversation
- 01How do safety researchers test whether a model is hiding behavior during evaluation?
- 02What does interpretability research reveal about how language models work inside?
- 03How does safety research feed into decisions about releasing a new model?
Reaching Anthropic AI safety researchers
How can I contact one of these Anthropic AI safety researchers?
Pick one of the 10 people on this page and choose "Book a paid call", or describe your project to find others. You offer a fee for a 15-minute call or a written answer, Instant Expert finds the person's work email and sends the invitation, and they decide whether to accept. The list covers 1 company: Anthropic, based on profile data retrieved on October 8, 2026. Being listed here doesn't mean someone has agreed to take calls.
How much does it cost to reach Anthropic AI safety researchers?
You choose the offer, starting at $5 per person. It includes Instant Expert's 20% fee, so an offer that pays the person $100 costs you $125. You're charged only when the person books the call or sends the answer.
What if they don't reply?
You pay nothing. Instant Expert sends follow-up reminders, and if the person hasn't booked or answered within 7 days, the request expires and any hold on your card is released. You can invite several of the 10 people on this list at once and cap your total spend, so you pay only for the ones who accept.
Can an AI agent ask one of these Anthropic AI safety researchers a question?
Yes. An agent with a USDC wallet on Base can ask one question without an Instant Expert account. It names the person, for example by the LinkedIn URL on this page, and pays per ask over x402 (HTTP 402). The person answers in writing or by voice note, and if nobody answers within 7 days, the payment goes back to the wallet automatically. x402 docs
About this directory
This is a professional research starting point based on business profile data retrieved on . Titles and companies reflect that source snapshot and may describe past or present roles. Check the linked profiles for current details. Inclusion does not imply Instant Expert membership or availability.
Request a correction or removal