Overview
Research Scientist on Anthropic’s Frontier Red Team (FRT), focusing on AI-empowered cybersecurity to defend against advanced AI-enabled cyber threats.
What you'll do
- Develop systems, tools, and frameworks for AI-empowered cybersecurity.
- Design and run experiments to elicit and evaluate autonomous AI cyber capabilities.
- Build infrastructure for evaluating/enabling AI systems in security environments.
- Translate technical findings into demonstrations and artifacts for policymakers and the public.
- Collaborate with external experts to scope and validate research directions.
- As a senior candidate, define problems, own the technical roadmap, and manage cross-functional partner relationships.
What you'll need
- Deep expertise in cybersecurity or security research.
- Experience doing technical research with LLM-based agents or autonomous systems.
- Strong software engineering skills, particularly in Python.
- Ability to own problems end-to-end across technical and non-technical components.
- Comfort working on sensitive projects requiring discretion and integrity.
- Proven ability to lead cross-functional security initiatives.
- Minimum education: a Bachelor’s degree or an equivalent combination of education, training, and/or experience.
Details
- Location: exclusively hiring in SF; all hires must relocate before starting.
- Work mode: location-based hybrid; expected to be in an office at least 25% of the time.
Read the full description and apply on the company’s own careers page.
