Remote AI Red Team Safety Specialist: Adversarial Testing

Mercor is seeking a remote red-team data expert to probe AI models with adversarial inputs, surface vulnerabilities, and generate high-quality data for safer AI systems. English and Thai fluency are required, with topics ranging from bias to harmful content handled under clear guidelines.

You’ll document results and collaborate across projects for robust safety testing. This role focuses on reproducible artifacts, standardized taxonomies, and cross-functional communication to stakeholders,

For the Remote AI Red Team Safety Specialist:
Adversarial Testing position at Obsidian, we are reviewing applications now.

Join us at Obsidian as our next Remote AI Red Team Safety Specialist:
Adversarial Testing in San Francisco, CA, United States.

We are currently recruiting a Remote AI Red Team Safety Specialist:
Adversarial Testing for our team in San Francisco, CA, United States.

This is an excellent position to take on the Remote AI Red Team Safety Specialist:
Adversarial Testing role at Obsidian.