Senior Quality Engineer - Tellent Intelligence (AI)
Tellent
Apply on the employer’s site →
Note: The listed salary range is based on the salary range for the Netherlands. Salary ranges may vary by location. About the Role As a Senior Quality Engineer – Tellent Intelligence (AI), you'll own and grow the quality of the AI-powered experiences built by our Tellent Intelligence team alongside our existing QE team. You'll help shape how we test applications powered by large language models (LLMs) and AI agents, ensuring they are reliable, safe, and deliver high-quality experiences for our customers. You'll expand our end-to-end test coverage in Playwright and help build robust approaches for validating AI-powered systems, where quality extends beyond functional correctness. This is a hands-on, collaborative role with genuine ownership, direct impact on product development, and the opportunity to shape how we test AI at Tellent. Your 12-Month Journey During your first 3 months: You'll get to know our Tellent Intelligence domain, engineering practices, AI-powered features, and quality standards. You'll learn our testing framework and development workflow while contributing to automated, exploratory, and AI-focused testing. Within 6 months: You'll take ownership of quality across key AI-powered features, expand our Playwright test coverage, and work closely with engineers to validate AI behaviour, prompts, and model-driven functionality throughout development. After 1 year: You'll be a trusted quality partner within the Tellent Intelligence team, driving improvements to our AI testing strategy, strengthening our automation framework, and helping shape how we build reliable, safe, and responsible AI experiences across Tellent. What You'll Be Doing Work closely with fellow Quality Engineers to bring our test automation strategy to life across the Tellent Intelligence domain, taking shared ownership and continuously improving it as our platform evolves. Partner with developers, AI engineers, and fellow QEs to embed quality early in the development process, sharing knowledge and shaping testing practices collaboratively. Design and execute comprehensive test plans, test cases, and automated test suites across frontend, backend, and AI-powered functionality. Develop into a product domain expert, using your understanding to identify risks early and guide quality decisions across the Tellent Intelligence domain. Design and execute testing strategies for AI-powered features, validating not only functional correctness but also the quality, relevance, consistency, and safety of AI-generated outputs. Develop approaches for testing non-deterministic systems by creating evaluation datasets, defining quality benchmarks, and identifying hallucinations, bias, regressions, and prompt-related issues as models and prompts evolve. Partner with engineers to validate prompt changes, AI agent behaviour, and safety guardrails, ensuring our AI behaves reliably and responsibly before reaching customers. Continuously improve how we evaluate AI quality by helping establish best practices, quality metrics, and testing frameworks for LLM-powered applications. What You Bring Strong QA experience: Several years of hands-on quality engineering, with senior-level ownership of testing for complex web applications. AI quality mindset: Experience testing AI-powered applications, LLM-based products, conversational AI, or machine learning systems is a strong plus. If you haven't worked directly with AI before, you're excited to learn and apply quality engineering principles to this rapidly evolving space. E2E automation: Experience building and maintaining end-to-end test suites in Playwright. API & backend testing skills: Experience testing APIs and backend services. Balance of product and technical thinking: Equally at home discussing product behaviour and digging into technical detail. Understanding of AI testing challenges: Familiarity with concepts such as prompt engineering, AI agents, hallucinations, model bias, evaluation datasets, and AI safety…
Listing via Arbeitnow.