Staff + Software Security Engineer, Labs
Anthropic· Security
San Francisco, CA, New York, NY, Seattle, WA$320k - $485kFull-timePosted 2w ago
About the role
Security Labs at Anthropic conducts high-risk security research to push beyond current industry protections, focusing on end-to-end ownership of security bets from prototyping to hand-off or documented learnings. The role combines strong software engineering with deep specialization in areas like firmware/hardware security, applied cryptography, OS/kernel/hypervisor internals, formal methods, reverse engineering, or high-assurance systems, and requires cross-domain collaboration with research and infrastructure teams.
Responsibilities
- Own Security Labs projects end to end. Scope the bet, build the prototype, run it against real workloads, and bring it to either a hand-off or a documented exit
- Stand up novel security infrastructure fast (isolated clusters, attestation chains, hypervisor and runtime work, verification tooling) optimizing for learnings rather than permanence
- Find the receiving team early, bring them along while you build, and hand them something they actually want to own
- Work embedded with research and infrastructure teams (Pretraining, RL, Inference, Compute) to test whether their workflows survive proposed changes, and document precisely where they don’t
- Turn experimental results into short writeups shaping Anthropic's long-term security architecture and into costed contingency plans
- Help pick the next round of bets and influence the industry to get better along the way
Qualifications
- Genuinely care about where AI is heading and want to work on security problems that determine whether it goes well
- Deep real-world expertise in at least one area uncommon for software engineers (e.g., firmware/hardware security, applied cryptography, OS/kernel/hypervisor internals, formal methods and verification, reverse engineering and exploit development, or high-assurance/cross-domain systems)
- Built and shipped things under your own direction (e.g., founded a company or research group, maintained an open-source project, or shipped research that changed the field)
- Proven track record of choosing a problem and seeing it through, not just executing a plan
- Comfortable jumping between domains and layers of the stack
- Ran prototypes/experiments aimed at answering hard questions rather than shipping a permanent system
- Clear writing to turn weeks of work into action-ready documents
- Willing to adapt and be the least-expert in a room full of specialists
- Strong programming skills (Python plus Rust/Go/C/C++) and ability to stand up real infrastructure
Skills
Required:PythonRust/Go/C/C++
Benefits
- Competitive compensation and benefits
- Optional equity donation matching
- Generous vacation and parental leave
- Flexible working hours
- Office space for collaboration
Last updated Oct 7, 2026. Interested? Apply on the company site.
About Anthropic
building reliable, interpretable, and steerable AI systems
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
ai-infrastructure-and-developmentliquid-ai-recruiting-targetsetter-30setter-30-2026-q1wing-list-2026wing-list-2026-giga-stage
More open roles at Anthropic
- Technical Program Manager, Science Strategy & Communications5d agoHybrid (San Francisco, CA), Hybrid (New York City, NY) · Technical Program Management
- Technical Program Manager, Inference5d agoHybrid (San Francisco, CA), Hybrid (New York City, NY) +1 more · Technical Program Management
- Technical Program Manager, SOX Compliance5d agoHybrid (San Francisco, CA), Hybrid (New York, NY) · Technical Program Management
- Technical Program Manager, Corporate Engineering5d agoHybrid (San Francisco, CA), Hybrid (New York City, NY) · Technical Program Management
- Staff+ Software Engineer, VectorDB5d agoHybrid (New York City, NY), Hybrid (Seattle, WA) +1 more · Software Engineering - Infrastructure