The individual in this role ensures the quality, reliability, and risk compliance of solutions throughout the ADLC lifecycle. Responsibilities include designing and managing test suites and cases using Eval Driven Development methodologies. The role involves orchestrating end-to-end system integration testing and overseeing the execution of test suites by AI agents. Additionally, the professional leads reflection phases to generate insights for optimizing agent harnesses and authors custom evaluation instructions. Finally, the position requires providing formal quality score sign-offs before governance and production releases.

The role requires proficiency in Python and the pytest framework. Candidates must possess experience with GitHub Copilot for both CLI and IDE integration. Additionally, expertise in data pipeline testing and knowledge of the risk domain are necessary for this position.