Security Engineer, Offensive Security

This security engineering role focuses on offensive security operations to safeguard Anthropic's AI systems. The engineer will conduct red and purple team engagements simulating advanced threat actors across cloud, endpoints, and bare metal, perform penetration tests, and collaborate cross-functionally on AI-specific attack scenarios. The role involves developing AI-assisted security testing tooling and presenting findings to technical and executive audiences to inform security roadmaps.

The role requires 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, or CI/CD pipelines, a track record of discovering novel attack vectors and chaining vulnerabilities, experience conducting adversarial simulations against well-defended environments, and strong engineering skills in Python, Go, or similar. Collaborative approach and ability to write clear,