Remote AI Safety Red Teamer – Adversarial Testing

Mercor is seeking an AI Safety Red Teamer to join our remote team. You will design adversarial prompts to stress-test frontier AI models, identify jailbreaks and unsafe behaviors, and evaluate model robustness across misinformation, cyber, biosecurity, and political content.

You will document vulnerabilities, contribute to safety benchmarking and red-teaming reports, and collaborate with AI researchers to improve alignment, robustness, and safety.

We invite applications for the Remote AI Safety Red Teamer – Adversarial Testing position located in United Kingdom.

This role, Remote AI Safety Red Teamer – Adversarial Testing at Mercor, could be your next move.

Are you ready to take on the Remote AI Safety Red Teamer – Adversarial Testing role at Mercor?

We would love to welcome a new Remote AI Safety Red Teamer – Adversarial Testing to our organisation in United Kingdom.