AI Safety Expert - Red Team

mercor; Netherlands; Remote; EUR 59,000 - 76,000; Full time

Job summary

Mercor is seeking AI Safety Experts to join our remote team, focusing on English & Dutch language contexts. This contract role offers hourly compensation between $48 and $62 and the flexibility of remote work across international time zones.

You will red-team conversational AI models, annotate failures, classify vulnerabilities, and document actionable reports to help customers improve safety and robustness of AI systems.

Qualifications

• Fluent in English and Dutch with ability to explain risks clearly to diverse stakeholders.
• Experience in AI adversarial testing, cybersecurity, or socio-technical probing.
• Ability to work independently and meet deadlines.

Responsibilities

• Red team conversational AI models to identify jailbreaks and misuses.
• Annotate failures and classify vulnerabilities; flag systemic risks.
• Apply taxonomies, benchmarks, and playbooks to ensure consistent testing.
• Document reproducibly to produce reports and datasets.
• Work independently and asynchronously to meet deadlines and improve AI performance.

Skills

Fluent English

Fluent Dutch

Red teaming experience

Risk communication

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 & Dutch. Type: Contract. Compensation: $48–$62/hour. Location: Remote.

Role 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 ensure 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 & Dutch.
• Prior red teaming experience in AI adversarial work , cybersecurity , or socio-technical probing.
• Ability to explain risks clearly to technical and non-technical stakeholders.

Preferred

• Experience with Adversarial ML , cybersecurity , and socio-technical risk.
• Skills in creative probing such as psychology, acting, or unconventional adversarial thinking.

Originally posted on Himalayas