AI Safety Red Teamer, English and Malayalam
· US ·
- Work mode
- Remote
- Category
- Security
Red Teamer probes conversational AI models in English and Malayalam with adversarial inputs — jailbreaks, prompt injection, bias exploitation, and multi-turn manipulation — and reviews outputs on sensitive topics to produce actionable safety data. A text-based remote role based in the US.
Help make conversational AI safer by probing models with adversarial inputs, identifying vulnerabilities, and producing actionable red-team data. This text-based remote role focuses on testing AI behavior across sensitive areas, including bias, misinformation, and harmful behaviors. Key Responsibilities Test conversational AI models and agents for jailbreaks, prompt injection, misuse cases, bias exploitation, and multi-turn manipulation. Review AI outputs involving sensitive topics, with higher…