Generative AI Safety & Bias Evaluator

TELUS International AI Inc. seeks a Trust & Safety Evaluator to conduct adversarial testing and safety evaluations of generative AI features, using deep cultural and linguistic knowledge to identify subtle risks.

The role involves designing challenging queries, simulating conversations, and creating attack scenarios, with a focus on bias detection and safety system understanding. On-site in Tampere, Finland, full-time employment with standard hours.