4 of 4 Test Automation Jobs in Hungerford

features in Klipboard products, where a confidently wrong price, part match or stock answer is worse than no answer.Build evaluation into everything – test prompts against real business cases at scale, measure quality honestly, and treat “it looked fine when I tried it“ as the start of the work … Claude, Llama and equivalents)AI coding tools: GitHub Copilot, Cursor or equivalentsPrompt engineering, context design and agentic workflow frameworksEvaluation harnesses, evaluation datasets and automated test suites for AI outputsRetrieval-augmented generation (RAG), vector search, embeddings and retrieval pipelines (desirable)LLM orchestration frameworks (LangChain, Semantic Kernel or equivalents – desirable)Technical ...

experience working with Large Language Models in commercial environments. Strong experience with prompt engineering, context engineering and structured outputs . Experience building evaluation frameworks, test harnesses or datasets for LLM outputs. Evidence of using evaluation and data to measurably improve AI quality . A proven ability to mentor, coach … pipelines LLM orchestration frameworks such as LangChain, Semantic Kernel or equivalents Multiple LLM providers and an understanding of their respective strengths and weaknesses Automated test suites and evaluation datasets for AI outputs AI adoption within established or legacy codebases SaaS environments Distributive trades, rental, retail, automotive aftermarket or garage ...

weeks, and know the difference between a corner that can be cut and one that cannot. Build evaluation alongside the feature, not after it – test against real business cases, measure quality honestly, and let the numbers settle arguments. Handle the unglamorous parts well: error handling, fallbacks when a model … trades, rental, retail, automotive aftermarket parts or garage management. Experience modernising or extending long-lived systems, in .NET or elsewhere. Familiarity with evaluation frameworks, test datasets or automated quality pipelines for AI outputs. Klipboard is embracing AI at pace across our products and ways of working. We’re looking ...

weeks, and know the difference between a corner that can be cut and one that cannot.Build evaluation alongside the feature, not after it – test against real business cases, measure quality honestly, and let the numbers settle arguments.Handle the unglamorous parts well: error handling, fallbacks when a model misbehaves, latency … sectors: distributive trades, rental, retail, automotive aftermarket parts or garage management.Experience modernising or extending long-lived systems, in .NET or elsewhere.Familiarity with evaluation frameworks, test datasets or automated quality pipelines for AI outputs.Klipboard is embracing AI at pace across our products and ways of working. We’re looking ...