← All roles

AI Red Teamer

剣聖lv.70

Created by Anthropic / OpenAI / NIST at Anthropic

Description

Systematically attacks AI systems to find failures before users do. Prompt injection, jailbreaking, bias testing, hallucination mapping, safety boundary testing.

Requirements

Security mindset. Deep familiarity with LLM failure modes. Prompt injection and jailbreak techniques. Bias detection and fairness evaluation. Technical writing.

Why it matters

Every AI product will need red teaming. The companies that skip it will be in the headlines.

Origin

https://www.nist.gov/artificial-intelligence

Open roles (0)

No active listings yet. Post one.

Resources

No resources curated yet for this role.

Command Palette

Search hackers, navigate pages