AI Safety Specialist - Fully Remote

Responsibilities

• ▹red team AI models and agents
• ▹identify jailbreaks and prompt injections
• ▹annotate failures and classify vulnerabilities
• ▹apply taxonomies and testing playbooks
• ▹produce reproducible reports and datasets

Requirements

• ▹fluent in English and Dutch
• ▹prior red teaming experience in AI, cybersecurity or socio-technical work
• ▹ability to explain risks to technical and non-technical audiences

Nice to have

• ▹adversarial ML experience
• ▹cybersecurity background
• ▹creative, unconventional adversarial thinking

Soft skills

What we offer

• ▹$48-62/hour compensation
• ▹fully remote, independent, asynchronous work

About the company

Mercor connects elite creative and technical talent with leading AI research labs, headquartered in San Francisco.