Senior QAT (Quality Assurance Tester)

Senior QAT (Quality Assurance Tester)

Generative AI/RAG Platform (UK Public Sector)

Salary: £65'000 per annum

Location: Newcastle, one day a week in the office

Security clearance: SC eligible, no SC needed

Overview

We are seeking an experienced Senior Quality Assurance Tester to lead testing strategy and execution for a Generative AI platform for a UK government department. This role goes beyond traditional functional QA. It includes evaluating AI output quality (answer accuracy, retrieval relevance, hallucination rate) alongside conventional API, integration and non-functional testing.

Key Responsibilities

Test Strategy & Planning

Define and own the test strategy across functional, non-functional and AI-specific quality dimensions (answer quality, retrieval accuracy, hallucination rate), covering RAG pipelines, prompt templates and agentic workflows.

AI Output Evaluation

Design and run structured evaluations of LLM outputs, working with engineering to track answer quality and hallucination rate over time, and flag regressions before release.

API & Integration Testing

Carry out manual and automated API testing (for example with REST Assured or similar tools) across the application logic that connects RAG pipelines to Legacy and multi-cloud systems.

Automation & CI/CD Integration

Build and maintain automated test suites integrated into CI/CD pipelines (for example GitLab or Jenkins), enabling shift-left testing across the delivery life cycle.

Non-Functional Testing

Carry out performance testing (for example k6, Gatling or JMeter) and accessibility testing, so the platform is robust, responsive and inclusive under real government usage conditions.

Responsible AI Testing

Test that guardrails and human-in-the-loop checkpoints defined by policy and technical leads work correctly and consistently. This is a verification role, not a policy-setting one.

Agile Collaboration

Work within agile delivery teams, engaging with Product, Engineering and Policy stakeholders to embed testing throughout the sprint rather than treating it as a final gate.

Governance & Standards Compliance

Make sure testing and release evidence aligns with the GOV.UK Service Standard and departmental governance, supporting evidence-gathering for service assessments where required.

Documentation & Handover

Contribute test plans, evaluation frameworks and results to "Docs-as-Code" artefacts supporting the OKUA knowledge-transfer framework, so internal government engineers can understand how quality was assured.

Required Skills & Experience

• Experience in a modern programming language (preferably Java or Python), version control and coding standards

• Experience in manual API testing and tools

• Experience building and maintaining API automation testing, preferably with REST Assured or similar tools

• Adaptable team player, experienced in shift-left principles, including CI/CD tools such as GitLab, Jenkins or similar

• Experience conducting non-functional testing, including performance (k6, Gatling, JMeter or similar) and/or accessibility testing

• Experience working in an agile environment, with demonstrated testing activities and engagement with multiple stakeholders

• Comfortable working in secure, regulated environments and handling sensitive data appropriately

Desirable Experience

• Experience evaluating LLM or AI output quality (hallucination detection, answer relevance scoring, retrieval accuracy)

• Experience delivering digital services within UK central government or the wider public sector

• Familiarity with GOV.UK Service Standard expectations and service assessment processes

• Exposure to open-source LLM tooling or evaluation frameworks

• Familiarity with AI/ML tooling on AWS, Azure or GCP