AI Safety Expert, English – Dutch

This is a fully remote position, open to applicants in United States.

📋 Description

• Engage in red team assessments of conversational AI models and agents.

• Test for jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

• Create human data by annotating failures, identifying vulnerabilities, and highlighting systemic risks.

• Utilize taxonomies, benchmarks, and playbooks to ensure consistent testing methodologies.

• Generate reproducible reports, datasets, and actionable attack scenarios.

• Investigate AI outputs related to sensitive subjects such as bias, misinformation, and harmful behaviors.

• Discover vulnerabilities that automated testing may overlook.

• Broaden evaluation coverage and minimize surprises in production.

• Enhance customer AI systems through adversarial testing.

⛳️ Requirements

• Must possess native fluency in both English and Dutch.

• Previous experience in red teaming within AI adversarial contexts, cybersecurity, or socio-technical probing is essential.

• Capability to conduct adversarial probing of AI systems, including jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.

• Proficient in annotating failures, classifying vulnerabilities, and identifying systemic risks.

• Experience in adhering to taxonomies, benchmarks, and playbooks.

• Ability to create reproducible reports, datasets, and attack scenarios.

• Skill in articulating risks clearly to both technical and non-technical stakeholders.

• Must be adaptable across various projects and clients.

• H1-B and STEM OPT candidates are not eligible for support.

• This position is for independent contractor engagement.

🏝️ Benefits

• Fully remote position.

• Flexible scheduling tailored to your availability.

• Weekly payments processed through Stripe or Wise.

• Project durations may vary based on needs and performance metrics.

• Participation in higher-sensitivity projects is optional.

• Clear guidelines and wellness resources are provided for handling sensitive content.

• Up to $250 referral bonus for each successful referral.

• Competitive compensation package.

• Opportunity to collaborate with leading researchers in the field.

• Reasonable accommodations available upon request.