أبلاي إيدج ابدأ البحث عن عمل

Senior Quality Assurance Engineer

Searchability® · Abu Dhabi Emirate, United Arab Emirates

قدّم وتابع مع أبلاي إيدج
Senior QA Automation Engineer (AI / LLM)Senior QA Automation Engineer (AI, LLM, Conversational Agents), Leading AI Company, Abu DhabiKEY POINTSHybrid in Abu Dhabi, 2 to 3 days a week onsiteOwn quality across cutting edge generative AI and conversational agent productsReal LLM testing, hallucination, bias, toxicity and PII checks, golden sets, non deterministic assertionsSenior role, 8 or more years in QA automation with genuine AI testing depthArabic speaker essentialSalary around 30,000 AED per month, with room for exceptional candidatesABOUT THE CLIENTWe are supporting a leading AI company building generative AI and conversational agent products at serious scale. This is a frontier AI organisation with the ambition and resources to match, and quality engineering sits right at the heart of how they ship responsible, reliable AI.This is a modern QA role at the edge of the field, testing non deterministic AI systems rather than traditional regression work. If you have moved from classic QA automation into AI and LLM testing and want to work where that discipline is being defined, this is for you.THE ROLE, SENIOR QA AUTOMATION ENGINEERYou will own the quality strategy across complex data flows and AI driven products, with a particular focus on conversational agents. You will design generative AI testing scenarios, build evaluation frameworks for LLM behaviour, and run the safety and quality checks that keep these systems reliable and responsible. You will work closely with the ML and NLP teams to define what good looks like for agent performance.This is a hands on senior role combining deep automation expertise with strong analytical judgement, spotting the subtle inconsistencies in data and agent behaviour that matter.KEY RESPONSIBILITIESDesign and execute generative AI test scenarios, including exploratory testing for chatbot interactions, intent recognition, tone and edge case behaviourBuild LLM test designs, prompt and grounding validation, golden sets and non deterministic assertionsRun safety and quality checks for hallucination, bias, toxicity and PII leakageValidate structured and unstructured data outputs for consistency, accuracy and complianceEstablish real time testing approaches including streaming data validation and API monitoringCollaborate with ML and NLP teams to define evaluation metrics for agent performanceIntegrate AI tools such as Copilot and Claude into the QA lifecycle to accelerate test design, documentation and defect analysisESSENTIAL EXPERIENCE8 or more years in QA engineering, with proven automation testing experience5 or more years testing data systemsStrong experience using AI applications and LLM based assistants in testingIn depth automation skills in JavaScript and PythonAPI testing experience, manual and automatedFamiliarity with chatbot frameworks, LLMs and conversational testingExposure to QA automation tools such as PyTest, Postman and dbt testsStrong analytical skills and attention to detail across data and agent behaviourArabic speaker, this is essential given the team and the workEligible to be employed full time in the UAENice to have: experience defining quality standards for generative AI in a regulated or high compliance environmentWHAT'S ON OFFERSalary around 30,000 AED per month, with flexibility for exceptional candidatesThe chance to own quality engineering for frontier AI products at a serious AI organisationWork at the edge of LLM and conversational AI testing, where the discipline is still being definedHybrid working, 2 to 3 days onsite in Abu DhabiGenuine influence over how responsible, reliable AI gets shippedTO APPLYPlease apply via this advert or email Daniel.Jones@searchability.com directly. For further information, call 0203 763 3888 or 07704 152 638. By applying, you consent to us processing and submitting your application (subject to suitability) for this vacancy only.