jobs

Cyber Evaluations Engineer

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers,

Company

Anthropic

Location

San Francisco, CA; Washington, DC

Status

Open

Posted

2026-09-01T21:26:36+00:00

Anthropic is hiring Cyber Evaluations Engineers to build and run the evaluations that measure cyber-relevant capabilities and safeguard robustness in its models. The work includes designing capability, uplift and safety evaluations, running per-release robustness testing before launches, analysing jailbreak and prompt-bypass data, and prototyping detection probes for cyber misuse. Candidates need hands-on cybersecurity experience, Python, and a record of building or running evaluations or benchmarks on fixed timelines. Preferred: offensive-security research, abuse-data analysis, detection content such as Sigma or YARA, and a security clearance.