AI Safety Red Team Engineer - Remote

Mercor; Dublin; Remote; EUR 57,000 - 74,000; Full time

Job summary

Mercor connects elite creative and technical talent with leading AI research labs. We are recruiting AI Safety Experts to red team conversational AI models, identify jailbreaks, and assess risks for clients in a remote contract role.

Fluency in English and Danish is required, along with experience in AI adversarial work or cybersecurity. You will document findings and deliver actionable reports to multi-disciplinary stakeholders.

Qualifications

• Fluent in English and Danish.
• Experience in red teaming AI adversarial work or cybersecurity.
• Strong communication to explain risks to both technical and non-technical stakeholders.
• Ability to move across projects and customers.

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.
• Apply structure by following taxonomies, benchmarks, and playbooks to maintain consistent testing.
• Document reproducibly to produce reports, datasets, and attack cases that customers can act on.
• Work independently and asynchronously to meet deadlines while improving AI model performance.

Skills

Fluent in English

Danish

Job description

Mercor connects elite creative and technical talent with leading AI research labs. We are recruiting AI Safety Experts to red team conversational AI models, identify jailbreaks, and assess risks for clients in a remote contract role.

Fluency in English and Danish is required, along with experience in AI adversarial work or cybersecurity. You will document findings and deliver actionable reports to multi-disciplinary stakeholders.