Security Engineer, Offensive Security
Remote • Remote-Friendly, United States; San Francisco, CA | Seattle, WA | New York City, NY | Washington, DC
Posted 3d ago
About the job
Anthropic is building reliable, interpretable, and steerable AI systems to be safe and beneficial for users and society. The Security Engineering team is dedicated to safeguarding these AI systems and maintaining user trust. This involves developing critical security infrastructure, establishing secure development practices, and collaborating with research and product teams to operate as a world-class security organization.
Responsibilities
- Conduct red and purple team engagements simulating advanced threat actors across cloud infrastructure, endpoints, and bare metal deployments.
- Perform penetration tests on specific, high-value deployments.
- Contribute to the development of AI-assisted security testing tools and workflows.
- Collaborate with other security and engineering teams, focusing on AI-specific attack scenarios.
- Document and present findings to technical and executive audiences, translating attack narratives into actionable risk insights for security roadmaps.
Requirements
- 5+ years of hands-on experience in red teaming and offensive security operations.
- Deep expertise in at least two of: macOS security, Linux Security, Cloud security (GCP/AWS/Azure), Kubernetes, CI/CD pipelines.
- Proven track record of discovering novel attack vectors and creatively chaining vulnerabilities.
- Experience conducting adversarial simulations against well-defended environments.
- Strong engineering skills in Python, Go, or similar languages.
- Ability to write clear, action-driving findings that help teams understand risk and prioritize fixes.
- Collaborative approach, working closely with the blue team.
Benefits
- Annual compensation range: $300,000 - $320,000 USD
- Visa sponsorship available
- Hybrid work policy (minimum 25% in office)