Anthropic AI Security Fellow
Cybersecurity
WFA Digital Insight
Demand for AI security specialists has surged, with AI models now capable of outperforming humans in cybersecurity tasks. Anthropic's fellows program stands out for its focus on defensive AI use, and its commitment to fostering research talent. With the AI job market growing 25% in 2025, candidates with a strong background in AI security and a passion for research should take note of this unique opportunity.
Job Description
About the Role
Anthropic is seeking an AI Security Fellow to contribute to the development of reliable, interpretable, and steerable AI systems. The fellow will work on an empirical project aligned with Anthropic's research priorities, with the goal of producing a public output such as a paper submission.Responsibilities
- Conduct research on AI security and safety using external infrastructure
- Produce a public output such as a paper submission
Benefits
- Direct mentorship from Anthropic researchers
- Access to a shared workspace in Berkeley, California or London, UK
- Connection to the broader AI safety research community
How to Stand Out
- Familiarize yourself with Anthropic's research priorities and tailor your application to demonstrate your relevant skills and experience.
- Showcase your ability to work independently and collaboratively as part of a research team.
- Highlight any experience with open-source models, public APIs, or other relevant tools and technologies.
- Prepare to discuss your research interests and goals, and how they align with Anthropic's mission.
- Be prepared to provide examples of your previous research or projects, and explain how they demonstrate your skills and expertise.
This is a remote position listed on WFA Digital, the platform for professionals who work from anywhere. Browse more remote jobs across all categories.