Cybersecurity Evaluations Engineer; AI Safety & Robustness
Listed on 2026-10-01
-
Engineering
Cybersecurity, AI Evaluation
Anthropic is hiring Cyber Evaluations Engineers to build and run evaluations that measure cyber-relevant capabilities and safeguard robustness in our models. You will design new evals, run per-release robustness testing, and analyze data on jailbreaks and prompt bypasses to understand safeguards performance.
You will design detection probes and shape the layered abuse-detection architecture with the policy team, partnering with engineering to translate findings into improvements across models.
As a Cybersecurity Evaluations Engineer (AI Safety & Robustness), you will play an important part at Anthropic in United States.
We would love to welcome a new Cybersecurity Evaluations Engineer (AI Safety & Robustness) to our group in United States.
For the Cybersecurity Evaluations Engineer (AI Safety & Robustness) position at Anthropic, we are reviewing applications now.
Step into the Cybersecurity Evaluations Engineer (AI Safety & Robustness) role at Anthropic in United States and grow with us.
(If this job is in fact in your jurisdiction, then you may be using a Proxy or VPN to access this site, and to progress further, you should change your connectivity to another mobile device or PC).