Remote Adversarial ML Specialist AI Safety Red Team

Mercor is building a remote red team for AI safety. You will lead adversarial testing of conversational AI models, focusing on jailbreaks, prompt injections, misuse, and bias exploitation. You will generate high-quality human data, annotate failures, classify vulnerabilities, and document findings in reproducible reports and datasets that help customers strengthen their AI systems. Ideal candidates bring prior red teaming experience, a curious adversarial mindset, structured approaches, and the