Security Labs is an experimental team within Anthropic that tackles high‑risk, high‑value security projects for AI systems. Engineers own end‑to‑end projects—scoping, prototyping, testing against real workloads, and handing off deliverables. The team builds infrastructure like isolated clusters, cryptographic verification mechanisms, hypervisor isolation, and formally verified pipelines, and converts findings into architectural guidance and contingency plans.
Security Labs Engineer at Anthropic
On-site - San Francisco, CA
More jobs at AnthropicRequirements
Skills
- Strong software engineering foundation
- Depth in firmware or hardware security, applied cryptography, OS/kernel/hypervisor internals, formal methods, reverse engineering, or high‑assurance cross‑domain systems
- Experience building and shipping prototypes under own direction
- Ability to work across multiple layers of the stack
- Track record of leading projects from conception to completion
Responsibilities
- Own Security Labs projects end to end, from scoping to prototype build and hand‑off or exit
- Stand up novel security infrastructure such as isolated clusters, attestation chains, hypervisor and runtime work, and verification tooling
- Identify receiving teams early and hand off deliverables they can own
- Collaborate with research and infrastructure teams to test workflow viability and document gaps
- Transform experimental results into short write‑ups that influence Anthropic’s long‑term security architecture and contingency plans
- Help prioritize future bets and shape industry practices
Technologies
Zero‑knowledge proofsAttestation chainsMicroVM substratesFormally verified pipelinesHypervisor-level isolation
See if your resume is ready for this job
See how our AI can optimize your resume and improve your chances for this role.