Mercor is building a remote red-team for AI safety, focusing on adversarial inputs, jailbreaks, and prompt injections to stress-test AI models. You will generate high-quality human data, annotate failures, and classify vulnerabilities, following established taxonomies and playbooks.
The role values curiosity, structured thinking, and explicit communication to stakeholders across technical and non-technical audiences. Remote, flexible collaboration across projects and customers is offered.
#J-18808-Ljbffr
📌 Remote AI Adversarial Red Team Specialist (EN/ID) (Melbourne)
🏢 Mercor
📍 Melbourne
Reply to this offer
Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.