AI Test Engineer

SANSS Consulting Limited is seeking a detail-oriented AI Test Engineer to join our delivery team. In this role you will be responsible for testing software applications for functionality, performance, and reliability across the full development lifecycle. You will create and execute test plans, identify and document defects, and work closely with developers, business analysts, and project stakeholders to deliver software that meets both technical specifications and business requirements.

You will work closely with the Product and Business teams to define and understand end-user requirements, test our Artificial Intelligence platform, and ensure the quality and reliability of our AI-powered chatbot built using ChatGPT. You will be responsible for testing prompts, creating test cases, and validating the performance of AI models.

• Test software applications for functionality, performance, and reliability.
• Work closely with the Product and Business teams to define and understand end-user requirements.
• Test the Artificial Intelligence platform and ensure the quality and reliability of the AI-powered chatbot built using ChatGPT.
• Test prompts, create test cases, and validate the performance of AI models.
• Create and execute test plans, test cases, and test documentation.
• Perform functional, regression, compatibility, and usability testing.
• Identify, track, and verify software defects through to resolution.
• Work closely with developers and stakeholders to resolve issues.
• Analyse requirements and prepare detailed test scenarios.
• Produce test reports and provide quality improvement recommendations.

• Experience in software testing / quality assurance.
• Solid understanding of the software development lifecycle (SDLC) and testing methodologies (Agile, Scrum, Waterfall).
• Hands-on experience writing and executing test cases, and logging defects.
• Experience with test-management and defect-tracking tools (e.g. Jira, Zephyr, TestRail).
• Familiarity with test-automation tools or frameworks (e.g. Selenium, Cypress, Playwright, Postman, JMeter).
• Understanding of AI/LLM concepts, prompt testing, and validating model outputs.
• Working knowledge of SQL for data validation.
• Strong analytical, problem-solving, and documentation skills.
• Excellent written and verbal communication, with the ability to work effectively in a cross-functional team.

• Competitive salary and benefits package.
• Hybrid / flexible working arrangements.
• Professional development and certification support.
• Opportunity to work on varied projects across the UK