AI Safety Expert – Red Team, English and Danish

Job overview

The AI Safety Expert – Red Team, English and Danish role is fully remote; the posting does not specify a remote geographic scope. Compensation is $48–$62 per hour. Mercor connects creative and technical talent with leading AI research labs. The role tests conversational AI models and agents for vulnerabilities and misuse risks, then produces structured annotations and reproducible reports. This work gives customers actionable findings that can inform AI model performance and safety improvements.

What you'll do

• Red-team conversational AI models and agents for jailbreaks, prompt injections, and misuse cases
• annotate failures, classify vulnerabilities, and flag systemic risks
• follow taxonomies, benchmarks, and playbooks
• document reproducible reports, datasets, and attack cases
• work independently and asynchronously to meet deadlines.

What we're looking for

Skills & competencies

ai safety

red team

english and danish

remote

mercor

ai models

jailbreak testing

prompt injection

cybersecurity

vulnerability analysis

$48–$62/hour

Work arrangement

• Weekend coverage required

Why this role

Requires fluency in English and Danish and prior red-teaming experience in AI adversarial work, cybersecurity, or socio-technical probing; adversarial machine learning and penetration-testing experience are preferred.

About the employer

Mercor is hiring for this role. Industry: Research and Development in the Physical, Engineering, and Life Sciences (except Nanotechnology and Biotechnology). Sector: 54.