Do you get a kick out of breaking things, fixing them, and making sure they never break again? This isn't your run-of-the-mill testing gig.
You'll be working on Generative AI, putting guardrails around systems that don't always play by the rules.
If you've been testing LLMs for bias, an AI agent for safety, or a model output for accuracy, this is your chance to own the process
What you'll do
* Build and own test frameworks for Generative AI apps, LLMs, and agent workflows
* Automate testing for model outputs: accuracy, relevance, bias detection, safety validation
* Test everything from platform UI to conversational interfaces to MCP server integrations
* Design API test suites for REST, GraphQL, and custom AI services
* Define metrics and testing protocols for ethical AI and safety guardrails
* Push systems to the limit with performance and load testing for real-time AI workloads
* Work hand-in-hand with engineers to set standards and integrate QA into the build process
What you bring
* 7+ years in QA, including at least 2 years testing AI/ML or complex platforms
* Strong automation skills with Selenium, Playwright, and CI/CD pipelines
* Solid coding skills in Python and JavaScript/TypeScript for test automation
* API testing experience
* Hands-on work with Generative AI systems, LLMs, chatbots, or AI agents
Hybrid - 3 days per week in city centre office
Unfortunately, work permit sponsorship is not available for this role.
If interested, reach out on - even if your CV is a bit out of date.