AI Safety Expert - Red Teaming

Role Overview

Mercor connects elite creative and technical talent with leading AI research labs. As an AI Safety Expert - Red Teaming, you will red team conversational AI models and agents, conduct jailbreaks, and generate high-quality human data.
What You Will Do

Conduct jailbreaks, prompt injections, misuse cases, and bias exploitation. Generate high-quality human data, annotate failures, classify vulnerabilities, and flag systemic risks.
Why It Might Be a Fit

You will thrive on moving across projects and customers, and have strong communication skills to explain risks clearly to technical and non-technical stakeholders.
Requirements

- Fluent in English and Punjabi

- Prior experience in red teaming (AI adversarial work, cybersecurity, socio-technical probing)

- Strong communication skills

- Adaptable

Originally posted on Himalayas