QA Software Engineer (C2)

November 4, 2026

Hybrid

Middle

London, United Kingdom

Indeed

Description

QA Software Engineer (C2) for the Quality Enablement team, based in Bristol or London. The role focuses on building and maintaining automation frameworks that test AI-generated and AI-assisted code, and on developing agent-based tooling used by engineering teams. Work sits at the intersection of software development, quality engineering, and applied AI, with AI tools embedded in the daily workflow. The position is permanent and full-time.

Responsibilities

Build and maintain automation frameworks specifically for testing AI-generated code and AI system outputs
Create agent-based tools and solutions for Applied Engineering, Global Products teams, and developers
Use AI tools and techniques to build, refine, and scale internal testing tools and frameworks
Translate customer and stakeholder requirements into working tools, frameworks, and processes
Identify bottlenecks in code and architecture, build internal AI-driven tools, and participate in constructive code reviews
Partner with internal engineering teams to understand their AI deployment constraints and testing needs
Produce documentation and guidance so developers, QA teams, and clients can adopt the frameworks and agent tools
Take technical ownership of discrete components and features end-to-end, writing clean, well-tested code

Requirements

Proven experience as a QA Engineer, Automation Engineer, or Software Engineer with a strong quality and testing focus
Hands-on experience building test automation frameworks using Python, JavaScript/TypeScript, Java, Selenium, Playwright, Cypress, or similar
Experience working with or testing AI-generated code, AI models, or AI agents
Understanding of deterministic validation and non-deterministic evaluation of AI behavior and outputs
Understanding of the software development lifecycle (SDLC) and QA methodologies
Problem-solving skills with a solution-oriented mindset
Excellent communication skills to explain technical concepts to both technical and non-technical audiences
Experience building or integrating AI agents such as LangChain, AutoGen, custom agent frameworks, or MCP-based tooling
Understanding of prompt engineering and LLM evaluation techniques such as faithfulness, relevance, and LLM-as-a-judge patterns
Familiarity with CI/CD pipelines and integrating automated testing into deployment workflows
Experience with API testing