Mercor is assembling a red team to probe AI models with adversarial inputs, surface vulnerabilities, and generate data that improves safety for customers. This work is text-based, and participation in higher-sensitivity projects is optional and guided by clear guidelines and wellness resources.
As a member of the team, you will red team conversational AI models, generate high-quality human data, and document reproducible reports and datasets for customers to act on. Work from home is supported.