Anthropic Fellows Program — AI Security

About Anthropic

Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.

• 4 months of full‑time research
• Direct mentorship from Anthropic researchers
• Access to a shared workspace (in either Berkeley, California or London, UK)
• Connection to the broader AI safety and security research community
• Weekly stipend of 3,850 USD / 2,310 GBP / 4,300 CAD + benefits (vary by country)
• Funding for compute (approximately $15k per month) and other research expenses

The interview process will include an initial application & reference check, technical assessments & interviews, and a research discussion.

The expected base stipend for this role is 3,850 USD / 2,310 GBP / 4,300 CAD per week, with an expectation of 40 hours per week for 4 months (with possible extension).

Because the Fellows program aligns across teams, we consider candidates for all work streams by default. Some work streams may have unique assessment steps.

• Are motivated by making sure AI is safe and beneficial for society as a whole
• Are excited to transition into empirical AI research and would be interested in a full‑time role at Anthropic
• Have a strong technical background in computer science, mathematics, or physics
• Thrive in fast‑paced, collaborative environments
• Can implement ideas quickly and communicate clearly

• Strong background in a discipline relevant to a specific Fellows workstream (e.g. economics, social sciences, or cybersecurity)
• Experience in areas of research or engineering related to their workstream

• Fluent in Python programming
• Available to work full‑time on the Fellows program

Fellows will undergo a project selection & mentor matching process. Potential mentors include:

• Nicholas Carlini
• Keri Warr
• Evyatar Ben Asher
• Keane Lucas
• Newton Cheng

Past Fellows projects:

• AI agents find $4.6M in blockchain smart contract exploits:
  Winnie Xiao and Cole Killian, mentored by Nicholas Carlini and Alwin Peng
• Strengthening Red Teams: A Modular Scaffold for Control Evaluations:
  Chloe Loughridge et al., mentored by Jon Kutasov and Joe Benton

• Are motivated by reducing catastrophic risks from advanced AI systems
• Have contributed to open‑source projects in LLM‑ or security‑adjacent repositories
• Have demonstrated success in bringing clarity and ownership to ambiguous technical problems
• Have experience with pentesting, vulnerability research, or other offensive security work
• Have demonstrated willingness to do the "dirty work" that produces high‑quality outputs
• Have reported CVEs or been awarded bug bounties
• Have experience with empirical ML research projects
• Have experience with deep learning frameworks and experiment management

Work authorization in the U.S., U.K., or Canada is required; applicants must be located in the country of authorization during the program. Remote participation is possible for U.K., U.S., or Canada fellows. Visa sponsorship is not available; participants must have independent work authorization. The program runs for 4 months full‑time. If you cannot commit to the full duration, please note constraints in your application and we will review case‑by‑case.

We do not guarantee full‑time offers, but strong performance may lead to offers; historically 25–50% of fellows receive full‑time offers post‑program.

Anthropic is an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability, or other protected category.