AI Safety Expert - Red Team

mercor; Denmark; Remote; DKK 441,000 - 570,000; Full time

Job summary

Mercor seeks AI Safety Experts fluent in English and Danish for a remote contract role. You'll red-team conversational AI models, identify jailbreaks and prompts injections, and generate high-quality data to flag risks.

Strong communication is essential to explain findings to diverse stakeholders, and you will work across multiple projects with customers worldwide. Responsibilities include documenting reproducible reports, datasets, and attack scenarios, following established taxonomies and

Qualifications

• Fluent in English and Danish.
• 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.
• Ability to thrive on moving 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

Red teaming

Communication skills

Adaptability

Job description

About the job

Mercor connects elite creative and technical talent with leading AI research labs. Headquartered in San Francisco, our investors include Benchmark , General Catalyst , Peter Thiel , Adam D'Angelo , Larry Summers , and Jack Dorsey .

Position: AI Safety Experts — English & Danish

Type: Contract

Compensation: $48–$62/hour

Location: Remote

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 .

Qualifications Must-Have

• Fluent in English & 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.
• Ability to thrive on moving across projects and customers.

Preferred

• 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/disinfo probing, abuse analysis, conversational AI testing.
• Creative probing skills: psychology, acting, writing for unconventional adversarial thinking.