AI Safety Specialist - Bilingual

About the role

AI Safety Specialist - Bilingual at Mercor. Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases.

What you'll do

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, and misuse cases
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
• Apply structure by following taxonomies, benchmarks, and playbooks to ensure consistent testing
• Document reproducibly by producing reports, datasets, and attack cases that customers can act on
• Work independently and asynchronously to meet deadlines while improving AI model performance

What you need

• Penetration testing
• Writing
• Any graduate

Good to have

• Machine learning

What you get

• ₹1.5k–₹2.1k a hour