Company: Mercor
Location: London
Job Description:
Mercor is seeking a proactive AI red team specialist to probe conversational models for jailbreaks, prompts injections, and other misuse cases. You’ll generate high-quality adversarial data and document findings to help customers strengthen AI safety.
You’ll work across projects with strict frameworks, report risks clearly to technical and non-technical stakeholders, and adapt across multiple clients and contexts in a remote, international team.
#J-18808-Ljbffr…
Posted: October 22nd, 2026