Mercor is assembling a remote AI safety red team focused on testing conversational models with adversarial inputs, bias checks, and content probes. The role requires strong judgment of language and content in English and Malayalam, with rigorous attention to detail and a structured, guideline-driven approach.
You will generate reproducible data and attack case reports, contributing to safer AI for customers while collaborating with cross-functional teams in a adaptable, remote environment.
#J-18808-Ljbffr
📌 Bilingual AI Safety Red Team Analyst — Remote (Adelaide)
🏢 Obsidian
📍 Adelaide
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.