AI Safety Expert - Red Team

About the role

AI Safety Expert - Red Team at Mercor. Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation.

What you'll do

• Red team conversational AI models and agents. Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation
• Generate high-quality human data. Annotate failures, classify vulnerabilities, and flag systemic risks
• Apply structure using taxonomies, benchmarks, and playbooks to maintain testing consistency
• Document reproducibly. Produce 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

• Any graduate

Good to have

• Penetration testing
• Machine learning

What you get

• ₹1.9k–₹2.1k a hour