AI Safety Evaluator (English) – Content & Risk Review

TELUS International AI Inc. seeks a Trust & Safety Evaluator to conduct adversarial testing and safety evaluations of generative AI features.

You will craft diverse queries, design realistic conversations, and create attack scenarios while assessing cultural and linguistic nuances to identify safety risks. The role requires creative thinking about misuse, deep cultural knowledge, and the ability to produce high-quality feedback within deadlines.