AI Safety Experts — English & Norwegian

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an AI Safety Expert — English & Norwegian based in Canada.

This contract role offers an opportunity to help strengthen the safety and reliability of conversational AI systems and intelligent agents. You will conduct structured adversarial testing to uncover vulnerabilities, jailbreaks, prompt injections, misuse scenarios, and potential bias exploitation. Your work will help identify weaknesses before they can affect users or real-world deployments. You will generate high-quality human evaluation data by annotating failures, classifying vulnerabilities, and identifying systemic risks. The role combines creative problem-solving with rigorous testing methodologies, frameworks, and benchmarks. Working remotely across evolving projects, you will produce reproducible findings that help technical and non-technical stakeholders take meaningful action.