Cyber Evaluations Engineer
Anthropic · Remote-Friendly, United States; San Francisco, CA | Washington, DC
Design and run capability, uplift, and safety evaluations to assess cyber-relevant risk in new models. Execute per-release robustness testing and dig into data on jailbreaks and prompt bypasses. Design probes that detect cyber abuse in production and shape the overall detection a
- Role
- Engineering
- Remote policy
- fully-remote
- Salary
- USD 300k+
- Team
- Safeguards (Trust & Safety)
- Region
- Americas
- Posted
- 2026-09-01
- First seen
- 2026-10-31
- Last seen alive
- 2026-10-31
- Last verified
- 2026-10-31
- Verification
- AI-verified
- Source
- Anthropic careers
- Board
- greenhouse
Report expired / not remote
Check the employer's posting first. If it is gone or not actually remote, tell us via contact with "Cyber Evaluations Engineer at Anthropic"; the next ingest drops it.