AI Safety Expert (English & Norwegian)

📋 Description

• Conduct structured adversarial testing to uncover vulnerabilities in conversational AI models and
• Develop creative prompts and attack scenarios to probe model weaknesses.
• Generate high-quality evaluation data by annotating failures and classifying risks.
• Document findings with reproducible reports, datasets, and evidence.
• Communicate technical risks to both technical and non-technical audiences.
• Adapt testing across different projects, models, and customer needs while maintaining quality.

🎯 Requirements

• Fluent or professional-level proficiency in both English and Norwegian, with strong writing and
• Experience in AI red teaming, adversarial AI, cybersecurity, or socio-technical risk assessment.
• Ability to systematically probe systems for vulnerabilities and misuse.
• Experience applying structured frameworks and benchmarks to safety evaluations.
• Strong analytical, critical-thinking, and documentation skills.
• Attention to detail and ability to produce reproducible results.

🎁 Benefits

• Competitive contract compensation of $48–$62 per hour.
• Fully remote work environment.
• Flexible, project-based working structure.
• Opportunity to contribute to safety and responsible development of AI systems.
• Exposure to diverse AI models and adversarial testing methodologies.
• Opportunity to expand expertise in AI safety and security.