AI Safety Specialist — English and Dutch, Remote

Job overview

The AI Safety Specialist works remotely; the posting identifies the role as remote without specifying a geographic restriction. Compensation is $48–$62 per hour. Mercor connects technical and creative talent with AI research labs. The specialist red-teams conversational AI models and agents, documents vulnerabilities and systemic risks, and produces reproducible reports and datasets that help customers improve model performance and safety.

What you'll do

• Red-team conversational AI models and agents using jailbreaks, prompt injections, and bias exploitation
• annotate failures and classify vulnerabilities
• follow testing taxonomies, benchmarks, and playbooks
• document reports, datasets, and attack cases
• work independently and asynchronously to meet deadlines
• communicate risks to technical and non-technical stakeholders.

What we're looking for

Skills & competencies

ai safety specialist

remote

mercor

english and dutch

ai red teaming

jailbreak testing

prompt injection

bias testing

vulnerability analysis

ai model safety

cybersecurity

asynchronous work

$48–$62/hr

Work arrangement

• Weekend coverage required

Why this role

Fluency in English and Dutch and prior red-teaming experience are required; adversarial machine learning and cybersecurity experience are preferred.

About the employer

Mercor is hiring for this role. Industry: Web Search Portals and All Other Information Services. Sector: 51.