Talent Apply
Log in
All jobs
A

Cyber Evaluations Engineer

Anthropic
hybridUSD 300,000 - 405,000 / year
San Francisco, CA; Washington, DC

About this role

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, engineers, policy experts, and business leaders working together to build beneficial AI systems.

About the role

We're hiring Cyber Evaluations Engineers to build and run the evaluations that measure cyber-relevant capabilities and safeguard robustness in our models. You'll design new evals, run per-release robustness testing, and dig into data on jailbreaks and prompt bypasses to understand where our safeguards hold up and where they don't. You'll also design many of the probes that detect cyber abuse in production and help shape the overall detection architecture alongside the policy team.

Read the full description on TalentApply

Create a free account to see the complete job description, how well your CV matches this role, and apply in one click.

Clean up your CV

AI rewrites and formats your CV so it reads well and gets past screeners.

See how you score

Get your match percentage for this exact role before you spend time applying.

Apply professionally

Send a polished application in one click — no retyping the same details.

Track it easily

Follow every application in one place instead of digging through your inbox.

Free account · No card required

Your next opportunity starts here

Prepare, apply, track, interview and get hired — all from one platform, with AI in your corner.

Download app