AI Safety Expert - Adversarial ML

About the role

AI Safety Expert - Adversarial ML at Mercor. Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation.

What you'll do

• Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases, and bias exploitation
• Generate high-quality human data by annotating failures, classifying vulnerabilities, and flagging systemic risks
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain 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
• Writing

Good to have

• Penetration testing