AI Safety Red Teamer, English & Danish

Help make conversational AI systems safer by probing them with adversarial inputs, identifying weaknesses, and creating actionable red-team data. This remote, hourly role focuses on text-based evaluations of AI outputs, including optional higher-sensitivity work supported by clear guidance and wellness resources. Key Responsibilities

• Test conversational AI models and agents for jailbreaks, prompt injections, misuse cases, bias exploitation, and multi-turn manipulation.
• Review AI outputs involving sensitive subjects, including bias, misinformation, and harmful behaviors. Topics will be communicated before any content exposure.
• Annotate model failures, classify vulnerabilities, and identify systemic risks.
• Use established taxonomies, benchmarks, and playbooks to conduct consistent evaluations.
• Create reproducible reports, datasets, and attack cases that teams can use to strengthen AI systems.

• Native fluency in both English and Danish is required.
• Prior experience in AI red teaming, cybersecurity, or socio-technical risk assessment.
• Ability to test systems methodically using frameworks or benchmarks and communicate risks clearly to technical and non-technical audiences.
• Comfort adapting across projects and customer needs.

• Adversarial machine learning, including jailbreak datasets, prompt injection, RLHF or DPO attacks, or model extraction.
• Cybersecurity, including penetration testing, exploit development, or reverse engineering.
• Socio-technical risk research, including harassment or misinformation testing, abuse analysis, or conversational AI evaluation.
• Creative adversarial thinking informed by psychology, acting, or writing.

• Remote, hourly engagement.

• $48 to $62 per hour.