Quality and Testing associate

AIT is looking for an experienced Quality Engineer to join our technology delivery team and work on an exciting client project involving the development, testing and implementation of an AI agentic framework and agentic workflows.

This is a hands-on technical testing role for someone who has strong experience in Python-based test automation, API testing and software quality engineering, with an interest in or practical experience of testing AI/LLM-based applications and agentic workflows.

The successful candidate will work closely with software developers and technical leads to design and implement automated testing approaches for new AI-agentic solutions, ensuring that functionality, integrations, workflows and expected outcomes are thoroughly tested before release.

Key Responsibilities

• Develop and implement quality engineering and automated testing strategies for AI agentic applications and software workflows.
• Design, develop and maintain automated test frameworks and test suites using Python and Pytest.
• Create automated unit, integration, functional, system and regression tests.
• Test end-to-end AI agentic workflows, including agent interactions, workflow orchestration, tool/function calling and system integrations.
• Validate that AI agents select and execute the appropriate workflows and tools for defined business scenarios.
• Develop test scenarios covering normal, boundary, negative, exception and failure conditions.
• Use Postman to design and execute API test collections and validate API requests, responses, status codes, data and error handling.
• Use Newman to automate Postman collections and incorporate API regression testing into CI/CD pipelines.
• Test integrations between AI agents, APIs, databases, applications and other external services.
• Develop appropriate test data and automated test scripts to provide repeatable and reliable test coverage.
• Validate expected outputs from AI-agentic workflows against defined acceptance criteria and business requirements.
• Identify, investigate and document defects and work closely with developers to determine root causes and verify fixes.
• Perform regression testing following changes to application code, prompts, models, workflows or integrations.
• Support system and end-to-end testing across the complete agentic workflow.
• Establish quality controls, testing standards and quality gates for the AI-agentic development lifecycle.
• Maintain clear test documentation, test evidence and quality reports.
• Contribute to CI/CD automation and ensure appropriate automated tests are executed as part of the software delivery lifecycle.
• Continuously improve the test framework, automation coverage and overall quality engineering processes.

Essential Skills & Experience

• 3–4+ years' professional experience in software testing, quality engineering or test automation.
• Strong hands-on Python programming experience.
• Strong experience with Pytest and Python-based automated test development.
• Practical experience with Postman and Newman for API testing and automation.
• Experience developing and maintaining automated testing frameworks.
• Good understanding of REST APIs, JSON, HTTP methods and API integration testing.
• Experience with functional, integration, system and regression testing.
• Experience working within Agile/software development environments.
• Strong defect investigation, root-cause analysis and problem-solving skills.
• Ability to read and understand application code and work closely with software developers.
• Experience working independently and taking ownership of testing activities with limited supervision.

AI / Agentic Framework Experience

Experience with AI, LLM applications or agentic frameworks would be highly desirable.

Candidates with practical experience testing technologies such as LangChain, LangGraph, Microsoft/Azure AI services, OpenAI-based applications, RAG pipelines, AI agents or other agent orchestration frameworks are particularly encouraged to apply.

Experience in testing AI/agentic applications should ideally include:

• Testing agentic workflows and orchestration.
• Validating tool/function calling.
• Testing agent-to-system and API interactions.
• Creating test scenarios for different user prompts and workflow paths.
• Validating AI-generated outputs against defined expectations.
• Testing failure, exception and edge-case scenarios.
• Regression testing following changes to prompts, models, tools or agent workflows.
• Developing automated evaluation or validation approaches for AI-enabled applications.

Desirable

• Experience with LangChain or LangGraph.
• Experience with LLM/AI application testing or evaluation.
• Experience with REST API automation.
• Experience with Git and Git-based development workflows.
• Experience with CI/CD tools such as GitHub Actions, GitLab CI/CD, Azure DevOps or Jenkins.
• Experience with Docker or cloud-based application environments.
• Knowledge of databases and SQL.
• Experience working on software development projects involving automation or AI-enabled workflows.

Pay: £35,000.00-£42,000.00 per year

Work Location: Hybrid remote in London EC1N 8LE