Created by Anthropic / OpenAI / NIST at Anthropic
Systematically attacks AI systems to find failures before users do. Prompt injection, jailbreaking, bias testing, hallucination mapping, safety boundary testing.
Security mindset. Deep familiarity with LLM failure modes. Prompt injection and jailbreak techniques. Bias detection and fairness evaluation. Technical writing.
Every AI product will need red teaming. The companies that skip it will be in the headlines.
No active listings yet. Post one.
No resources curated yet for this role.
Search hackers, navigate pages