AI Safety Red Teamer, English & Telugu
· US ·
- Work mode
- Remote
- Category
- Security
Probes conversational AI systems with adversarial inputs — jailbreaks, prompt injection, bias exploitation, and multi-turn manipulation — to identify vulnerabilities, annotate model failures, and produce actionable safety data. Requires English and Telugu proficiency; it is a text-based, remote-friendly role.
Role Overview Help strengthen conversational AI systems by probing them with adversarial inputs, identifying vulnerabilities, and producing actionable safety 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 and annotate failures…