AI Test Engineer

What you will do

• Use AI-assisted engineering tools such as GitHub Copilot, Claude Code, or similar solutions to translate user stories, acceptance criteria, and UI/UX specifications such as Figma designs into test scenarios and executable automated tests.
• Build and improve AI-assisted testing workflows where requirements and design artifacts can be provided as context and used to generate, update, and expand automated tests with minimal manual scripting.
• Apply prompt engineering and context engineering techniques to provide AI tools with requirements, application context, coding standards, existing automation frameworks, and relevant design information so that generated tests are accurate and maintainable.
• Review, validate, debug, and refine AI-generated test scenarios and automation code rather than accepting generated output without verification.
• Identify opportunities to automate the test-development lifecycle, including requirements analysis, test generation, test-data creation, regression maintenance, failure analysis, and coverage expansion.

What you bring

• Experience
• 5–8 years of experience in software QA
• Hands-on experience using AI-assisted coding or engineering tools such as GitHub Copilot, Claude Code, or equivalent tools for software testing and test automation.
• Experience using requirements such as user stories, acceptance criteria, and UI/UX designs as context for AI-assisted generation of test scenarios and automated tests.
• Experience creating or configuring AI-assisted workflows that can transform requirements into executable automation, rather than using AI only for ad-hoc code completion or general-purpose prompting.
• Ability to provide application-specific context to AI tools, including existing automation code, framework conventions, requirements, design information, and test data, to improve generated test quality.
• Practical understanding of validating AI-generated tests for correctness, coverage, maintainability, traceability to requirements, and potential hallucinations or incorrect assumptions.
• Personal competencies
• Strong analytical thinking and problem-solving skills.
• Attention to detail and a risk-based approach to quality assurance.
• Curiosity and a proactive mindset when exploring complex workflows and edge cases.
• Willingness to adopt AI-assisted tools to improve productivity and test coverage.
• Effective communication and collaboration across technical and clinical teams.
• Ownership of testing outcomes, defect resolution, and release quality.

Who we are

Qualifications

• 5–8 years of experience in software QA
• Hands-on experience using AI-assisted coding or engineering tools such as GitHub Copilot, Claude Code, or equivalent tools for software testing and test automation.
• Experience using requirements such as user stories, acceptance criteria, and UI/UX designs as context for AI-assisted generation of test scenarios and automated tests.
• Experience creating or configuring AI-assisted workflows that can transform requirements into executable automation, rather than using AI only for ad-hoc code completion or general-purpose prompting.
• Ability to provide application-specific context to AI tools, including existing automation code, framework conventions, requirements, design information, and test data, to improve generated test quality.
• Practical understanding of validating AI-generated tests for correctness, coverage, maintainability, traceability to requirements, and potential hallucinations or incorrect assumptions.
• Personal competencies
• Strong analytical thinking and problem-solving skills.
• Attention to detail and a risk-based approach to quality assurance.
• Curiosity and a proactive mindset when exploring complex workflows and edge cases.
• Willingness to adopt AI-assisted tools to improve productivity and test coverage.
• Effective communication and collaboration across technical and clinical teams.
• Ownership of testing outcomes, defect resolution, and release quality.