Cultural Safety & Red-Teaming Expert (AI Community)

About the Role:

At TELUS Digital, we know that as AI becomes more powerful, the need for robust safety guardrails is paramount. We view you as our strategic "adversary." You will utilize your critical thinking and cultural depth to stress-test models, uncovering vulnerabilities that could lead to biased or harmful outputs. At TELUS, you are the final line of defense, ensuring that our AI remains a force for good in every corner of the world.

Key Responsibilities:

• Conduct high-stakes adversarial testing sessions, employing creative "jailbreaking" techniques to probe model vulnerabilities.
• Map regional social, political, and religious sensitivities to help the model avoid cultural "blind spots" in diverse global markets.
• Synthesize safety findings into comprehensive risk reports, collaborating with Policy Teams to update model safety guardrails.
• Evaluate the model’s ethical decision-making in "gray-area" scenarios, ensuring it prioritizes human safety and institutional values.