Research Engineer / Scientist, Frontier Red Team (Cyber)
San Francisco, CA
Posted 17d ago
About the job
The Frontier Red Team (FRT) is a focused technical research team dedicated to making the world safer in the era of advanced AI. This role involves researching and ensuring safety with self-improving, highly autonomous AI systems, particularly those with cyberphysical capabilities. You will build the tools and frameworks needed to defend against advanced AI-enabled cyber threats, working at the intersection of AI capabilities research, cybersecurity, and policy. This applied research has real-world stakes, informing company decisions, shaping policy discourse, and building technical defenses for the future of AI.
Responsibilities
- Develop systems, tools, and frameworks for AI-empowered cybersecurity, including autonomous vulnerability discovery and remediation, malware detection, network hardening, and pentesting.
- Design and execute experiments to elicit and evaluate autonomous AI cyber capabilities in realistic scenarios.
- Build infrastructure for evaluating and enabling AI systems to operate in security environments.
- Translate technical findings into demonstrations and artifacts for policymakers and the public.
- Collaborate with external experts in cybersecurity, national security, and AI safety.
- Set research strategy, define problems, own the technical roadmap, and manage cross-functional partnerships (for senior candidates).
Requirements
- Deep expertise in cybersecurity or security research.
- Experience with technical research involving LLM-based agents or autonomous systems.
- Strong software engineering skills, particularly in Python.
- Ability to own problems end-to-end, including technical and non-technical aspects.
- Experience designing and running experiments with rapid iteration.
- Comfort working on sensitive projects requiring discretion and integrity.
- Proven ability to lead cross-functional security initiatives and navigate complex organizational dynamics.
- Experience with offensive security research, vulnerability research, or exploit development.
- Research or professional experience applying LLMs to security problems.
- Track record in competitive CTFs, bug bounties, or other security-related competitions.
- Experience building security tools or automation.
- Track record of building demos or prototypes to communicate complex technical ideas.
- Experience working with external stakeholders (policymakers, government, researchers).
- Familiarity with AI safety research and threat modeling for advanced AI systems.