Staff Software Security Engineer Labs
AI safety and research company building reliable, interpretable, and steerable AI systems, including the Claude product family and developer platform.
Maintainer signals as of 9/25/2026
Funding history
About Anthropic
Anthropic PBC develops frontier AI systems and deploys them through Claude products and the Claude Platform, with a stated focus on safety, interpretability, and steerability.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will own experimental security projects from selecting the bet through prototype development, testing, handoff, or documented exit. You will build novel security infrastructure, work with research and infrastructure teams, document findings and contingency plans, and help select future security projects.
Requirements
- Depth in firmware or hardware security, applied cryptography, OS, kernel, hypervisor internals, formal methods, reverse engineering, or high-assurance systems
- Experience building and shipping systems independently
- Experience selecting problems and delivering outcomes
- Experience running prototypes or experiments
- Strong Python skills and proficiency in Rust, Go, or C/C++
- Clear technical writing
- Interest in AI security and defense
Responsibilities
- Scope, build, test, and hand off or document Security Labs projects
- Build experimental security infrastructure including isolated clusters, attestation chains, hypervisor work, and verification tooling
- Work with research and infrastructure teams to test proposed security controls
- Document experimental results and costed contingency plans
- Help select future security projects and influence security practices
Benefits
- Optional equity donation matching
- Generous vacation
- Parental leave
- Flexible working hours
