Anthropic Fellows Program, AI Security
Anthropic's mission is to create reliable, interpretable and steerable AI systems. The Anthropic Fellows Program fosters AI research and engineering talent by providing funding and mentorship to promising technical talent, regardless of previous experience. Fellows primarily use external infrastructure (open-source models, public APIs) to work on an empirical project aligned with Anthropic's research priorities, aiming to produce a public output such as a paper. The program runs 4 months full-time, with shared workspaces in London or Berkeley and remote fellows accepted in the UK, US or Canada. This workstream is AI Security, covering offensive security, vulnerability research and red-teaming of AI systems (past projects include AI agents finding $4.6M in blockchain smart-contract exploits and modular scaffolds for control evaluations).
Responsibilities
- ▹Work on an empirical AI security research project with the goal of producing a public output
- ▹Contribute to security-adjacent research such as red-teaming and control evaluations of AI systems
- ▹Conduct vulnerability research and offensive security work on AI and LLM systems
Requirements
- ▹Fluent in Python programming
- ▹Available to work full-time on the Fellows program
- ▹Strong technical background in computer science, mathematics or physics
- ▹Able to implement ideas quickly and communicate clearly
- ▹Motivated by making sure AI is safe and beneficial for society as a whole
- ▹Excited to transition into empirical AI research and interested in a full-time role at Anthropic
- ▹Work authorization in the US, UK or Canada and located in that country during the program (no visa sponsorship for fellows)
Nice to have
- ▹Motivated by reducing catastrophic risks from advanced AI systems
- ▹Contributions to open-source LLM- or security-adjacent repositories
- ▹Demonstrated success bringing clarity and ownership to ambiguous technical problems
- ▹Experience with pentesting, vulnerability research or other offensive security work
- ▹Willingness to do the "dirty work" that produces high-quality outputs
- ▹Reported CVEs or awarded bug bounties
- ▹Experience with empirical ML research projects
- ▹Experience with deep learning frameworks and experiment management
Soft skills
What we offer
- ▹Weekly stipend of 3,850 USD / 2,310 GBP / 4,300 CAD + benefits (vary by country), 40 hours/week for 4 months
- ▹Direct mentorship from Anthropic researchers
- ▹Access to a shared workspace in Berkeley, California or London, UK
- ▹Funding for compute (~$15k/month) and other research expenses
- ▹Connection to the broader AI safety and security research community