Remote AI Safety Red Team Specialist, English & Danish

United States Digital Space LLC; United States; Remote; USD 66,000 - 85,000; Part time

Job summary

Mercor is seeking AI Safety Experts to remotely assess and challenge conversational AI systems. You will red team models, annotate failures, and document vulnerabilities with actionable reports.

Ideal candidates have prior red teaming or adversarial ML experience, strong communication skills, and the ability to work asynchronously to meet deadlines. This is a contract role with hourly compensation of $48–$62.

Qualifications

• Fluent in English and Danish.
• Experience in AI adversarial testing or red teaming.
• Ability to explain risks to technical and non-technical stakeholders.

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

Skills

Fluent English

Fluent Danish

Red team experience

Strong communication

Job description

Mercor is seeking AI Safety Experts to remotely assess and challenge conversational AI systems. You will red team models, annotate failures, and document vulnerabilities with actionable reports.

Ideal candidates have prior red teaming or adversarial ML experience, strong communication skills, and the ability to work asynchronously to meet deadlines. This is a contract role with hourly compensation of $48–$62.