AI Safety Expert - Red Team

Responsibilities

• ▹Red team conversational AI models and agents to identify jailbreaks, prompt injections and misuse cases
• ▹Generate high-quality human data by annotating failures, classifying vulnerabilities and flagging systemic risks
• ▹Test consistently by following taxonomies, benchmarks and playbooks
• ▹Document reproducibly, producing reports, datasets and attack cases customers can act on
• ▹Work independently and asynchronously to meet deadlines while improving AI model performance

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 to technical and non-technical stakeholders
• ▹Ability to move across projects and customers

Nice to have

• ▹Experience in adversarial ML: jailbreak datasets, prompt injection, RLHF/DPO attacks, model extraction
• ▹Cybersecurity skills: penetration testing, exploit development, reverse engineering
• ▹Expertise in socio-technical risk: harassment and disinformation probing, abuse analysis, conversational AI testing
• ▹Creative probing skills: psychology, acting, writing for unconventional adversarial thinking

Soft skills

What we offer

• ▹Remote work
• ▹Hourly pay: $48-$62

About the company

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