Security Engineer, Offensive Security
Cybersecurity
WFA Digital Insight
As demand for AI safety and security grows, Anthropic is seeking a skilled Security Engineer to strengthen its systems. With a focus on offensive security, this role requires expertise in red teaming and AI-assisted security testing. Candidates should be prepared to demonstrate their ability to think creatively and collaborate with cross-functional teams. Before applying, consider how your skills align with Anthropic's mission to create reliable and interpretable AI systems.
Job Description
About the Role
Anthropic is a quickly growing group of researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems. The Security Engineering team is committed to safeguarding AI systems and maintaining user trust.Responsibilities
- Conduct red and purple team engagements simulating advanced threat actors across cloud infrastructure, endpoints, and bare metal deployments.
- Penetration test specific, high-value deployments.
- Contribute to AI-assisted security testing tooling and workflows.
- Work cross-functionally with other security and engineering teams on AI-specific attack scenarios.
- Document and present findings to technical and executive audiences.
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
- Track record of discovering novel attack vectors and chaining vulnerabilities creatively
- Experience conducting adversarial simulations against well-defended environments
- Strong engineering skills (Python, Go, or similar)
Nice to Have
- Prior work at organizations with state actor threat models
- Interest in AI safety and how security engineering contributes to responsible AI developments
How to Stand Out
- Develop a strong portfolio showcasing your experience in red teaming and offensive security operations, highlighting creative attack vectors and novel vulnerability chaining.
- Practice explaining complex technical concepts to non-technical audiences, as this role requires presenting findings to executive audiences.
- Familiarize yourself with AI-assisted security testing tooling and workflows, and be prepared to discuss your experience with these tools.
- Be prepared to discuss your approach to collaboration with cross-functional teams, including blue teams and other security teams.
- Research Anthropic's mission and values, and be prepared to explain how your skills and experience align with the company's goals.
This is a remote position listed on WFA Digital, the platform for professionals who work from anywhere. Browse more remote jobs across all categories.