Anthropic, a public benefit corporation headquartered in San Francisco, is seeking a Security Labs Engineer to join its experimental Security Labs team. The role focuses on high‑risk, high‑value security projects that push the boundaries of AI safety, ranging from cryptographic verification and isolated computing environments to formal verification of ML pipelines. The successful candidate will be a strong software engineer with deep expertise in areas like firmware, hardware security, applied cryptography, OS/kernel/hypervisor internals, formal methods, reverse engineering, or high‑assurance systems. Responsibilities include owning projects end‑to‑end, building novel security infrastructure, collaborating with research and infrastructure teams, and translating experimental findings into architectural guidance. Anthropic offers competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and a modern office space in San Francisco.
Security Labs Engineer at Anthropic
On-site - San Francisco, CA, USA
More jobs at AnthropicRequirements
Skills
- Strong software engineering foundation
- Real depth in at least one area such as firmware or hardware security, applied cryptography, OS/kernel/hypervisor internals, formal methods, reverse engineering, or high‑assurance systems
- Track record of building and shipping things under your own direction
- Ability to choose the problem yourself and see it through
- Comfortable jumping between domains and layers of the stack
- Experience running prototypes or experiments focused on answering hard questions rather than shipping permanent systems
- Genuinely care about where AI is heading and want to work on the security problems that determine whether it goes well
Responsibilities
- Own Security Labs projects end to end, from scoping the bet to building the prototype and running it against real workloads
- Stand up novel security infrastructure quickly (isolated clusters, attestation chains, hypervisor and runtime work, verification tooling)
- Identify the receiving team early, bring them along, and hand them deliverables they can own
- Work embedded with research and infrastructure teams to test their workflows and document failures
- Turn experimental results into short writeups that shape Anthropic’s long‑term security architecture and contingency plans
- Help pick the next round of bets and influence the industry to improve
Technologies
FirmwareHardware securityApplied cryptographyOS kernel internalsHypervisorFormal methodsReverse engineeringHigh‑assurance systemsZero‑knowledge proofsAttestation chainsHypervisor‑isolated microVM substrateVerification toolingML kernel
See if your resume is ready for this job
See how our AI can optimize your resume and improve your chances for this role.