AI Safety Expert – English, Danish

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

📋 Description

• Engage in red team activities for conversational AI models and agents.

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

• Create human data by annotating errors, categorizing vulnerabilities, and identifying systemic risks.

• Implement taxonomies, benchmarks, and playbooks to ensure consistent testing practices.

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

• Identify vulnerabilities that automated testing may overlook.

• Increase evaluation coverage and minimize unexpected production issues.

• Enhance customer AI systems through adversarial testing methodologies.

⛳️ Requirements

• Native proficiency in both English and Danish.

• Previous experience in red teaming related to AI adversarial activities, cybersecurity, or socio-technical probing.

• Capability to probe AI systems in an adversarial manner, including through jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.

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

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

• Proficiency in producing reproducible reports, datasets, and attack scenarios.

• Ability to clearly communicate risks to both technical and non-technical stakeholders.

• Adaptability across various projects and customers.

• Must hold independent contractor status.

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

🏝️ Benefits

• Work fully remotely.

• Enjoy a flexible schedule.

• Receive weekly payments via Stripe or Wise.

• Competitive compensation offered.

• Option to participate in higher-sensitivity projects.

• Access to clear content guidelines and wellness resources.

• Project durations may vary based on needs and performance.

• Earn referral payments of up to $250 for each successful referral.