AI Safety & Adversarial Testing Evaluator

TELUS Digital AI Data Solutions seeks a Trust & Safety Evaluator to conduct adversarial testing and safety evaluation of generative AI features. You will craft queries, assess generated content for safety, and provide critical feedback with deep cultural and linguistic insight.

Responsibilities include designing attack sequences, rating risk levels, and identifying biases or unsafe patterns. Strong English (India) proficiency and fast, accurate work in a dynamic setting are essential.