Staff+ Researcher Cybersecurity Products
AI safety and research company building reliable, interpretable, and steerable AI systems, including the Claude product family and developer platform.
Maintainer signals as of 9/23/2026
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 rapidly prototype and rigorously evaluate frontier-model capabilities for cybersecurity work. You will build evaluation datasets, harnesses, and scoring systems; assess model behavior in realistic and adversarial conditions; and translate promising capabilities into reliable customer-facing tools. You will share technical findings, track changes in model capabilities, and help set product priorities.
Requirements
- Deep expertise in a security domain such as vulnerability research, exploit development, reverse engineering, malware analysis, incident response, or offensive security
- Experience building AI-powered security tools or capabilities
- Ability to rapidly build and assess prototypes
- Experience designing rigorous evaluations and interpreting results
- Technical writing and communication skills
- 7+ years of security research, security engineering, or related experience
Responsibilities
- Prototype AI capabilities for cybersecurity work
- Design evaluations that measure model performance on security tasks
- Build evaluation datasets, harnesses, and scoring systems
- Engage with the cybersecurity community
- Operationalize promising capabilities with engineers and researchers
- Track changes in model security capabilities
- Share findings that inform product direction
Benefits
- Optional equity donation matching
- Generous vacation
- Parental leave
- Flexible working hours