AI Safety Expert - Red Teaming (English & Danish)

Responsibilities

• ▹Red team conversational AI models and agents to identify jailbreaks, prompt injections, misuse cases and bias exploitation
• ▹Generate high-quality human data by annotating failures and classifying vulnerabilities
• ▹Apply structure by following taxonomies, benchmarks and playbooks
• ▹Document findings reproducibly to produce reports, datasets and attack cases
• ▹Work independently and asynchronously to meet deadlines

Requirements

• ▹Fluent in English and Danish
• ▹Prior red teaming experience in AI adversarial work, cybersecurity or socio-technical probing
• ▹Strong communication skills to explain risks clearly to technical and non-technical stakeholders

Nice to have

• ▹Experience in Adversarial ML, cybersecurity or socio-technical risk analysis
• ▹Skills in creative probing such as psychology, acting or writing for unconventional adversarial thinking

Soft skills

What we offer

• ▹Compensation of $48-62 per hour
• ▹Fully remote, contract engagement

About the company

Mercor connects elite creative and technical talent with leading AI research labs; it is headquartered in San Francisco and backed by investors including Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers and Jack Dorsey.