Trust & Safety Evaluator with English from United Kingdom - TELUS International AI Inc. - Tampere, Finland

Trust & Safety Evaluator conduct adversarial testing and safety evaluation of generative AI features. Main tasks are crafting queries, evaluating the safety of generated content and providing critical feedback. This role requires creative thinking about potential misuse, deep cultural and linguistic knowledge, and the ability to identify subtle safety risks. KEY RESPONSIBILITIES - Write, review and evaluate diverse and challenging queries designed to test the system's limits and expose problematic outputs. Queries will target specific risk topics including explicit and/or offensive content - Design and execute sequences of queries simulating realistic, unfolding conversations. - Craft attack scenarios using techniques like crescendo attacks and context manipulation to test the system - Age-Appropriate Safety Evaluation: to guide adversarial query crafting and safety evaluation. - Assign risk ratings to AI Generated content based on safety guidelines. - Detect and articulate potential biases in system-generated content - Identify subtle unsafe elements, inconsistencies, or problematic implications - Evaluate specific cultural and language knowledge across different cultural contexts. - Leverage familiarity with relevant domains, genres, cultural references, and industry context. - Complete adversarial testing tasks within time constraints - Maintain high accuracy and attention to detail while working at pace. REQUIRED SKILLS - Language skills: English from United Kingdom as primary language is required. - Demonstrated in-depth cultural awareness of the United Kingdom together with business practices, market, social norms and values. - Candidates must be located in Finland and eligible to work fulltime in Finland. The role is on site in the Tampere office, remote work is not possible. - 2+ years of demonstrated professional experience in adversarial testing, red teaming, or similar security and safety evaluation work. - Experience crafting sequential adversarial queries and attack scenarios to test safety vulnerabilities across multi-turn conversations. - Demonstrated understanding of how online content safety policies are applied for explicit content. - Familiarity with safety taxonomies covering explicit inappropriate content. - Familiarity with behavioral patterns of younger audiences and how they interact with AI systems. - Ability to think critically about potential misuse, creatively craft queries and spot subtle unsafe elements, inconsistencies in generated outputs. - Excellent written communication skills. Ability to clearly describe identified issues, explain their nature, and articulate potential impact. - Capacity to document findings in a way that helps non-safety teams understand vulnerabilities and their significance. - Domain Knowledge: Familiarity with relevant domains, genres, cultural references, and industry context applicable to the features being tested.