AI Safety Expert - Adversarial ML

About the role

AI Safety Expert - Adversarial ML at Mercor. Red team conversational AI models and agents through jailbreaks, prompt injections, and misuse cases. Identify bias exploitation and multi-turn manipulation.

What you'll do

• Red team conversational AI models and agents through jailbreaks, prompt injections, and misuse cases. Identify bias exploitation and multi-turn manipulation
• 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

• Machine learning
• Penetration testing
• Writing
• Any graduate

What you get

• ₹1.5k–₹2.1k a hour