Join EY and forge a career path as unique as you are. Leverage our global scale, supportive culture, and advanced technology to reach your full potential. Your distinct perspective is vital in helping EY excel further. Become part of an organization dedicated to building an exceptional experience for yourself and fostering a better working world for everyone.

Lead the comprehensive test strategy, encompassing test plans, acceptance criteria coverage, and release-quality evidence for Agentic AI products. Develop and maintain automated regression and integration tests using tools like Playwright, Cypress, Selenium, and various API and Python testing libraries. Go beyond standard UI/API testing to validate agent behaviors, including tool selection, function call interactions, orchestration pathways, and human-in-the-loop controls. Design and execute diverse test scenarios, covering positive, negative, ambiguous, adversarial, and out-of-scope cases for all relevant acceptance criteria. Maintain evaluation datasets and regression suites for AI outputs, focusing on accuracy, consistency, factual grounding, and preventing regressions as prompts, models, or configurations evolve. Ensure test evidence is reviewable by SMEs by validating agent execution logs and traceability across all stages of agent operation.

Validate security and access control mechanisms, including negative authorization scenarios and agent/tool boundaries, collaborating with Security and Compliance experts on identified issues. Conduct defect triage, perform root-cause analysis with development teams, manage defect closure, and deliver clear quality and release-readiness reports, utilizing automated scripts and dashboards where feasible. Support performance and regression testing efforts, providing necessary evidence for system testing, UAT, and release gate approvals. A strong foundation in Python, automation, and agentic AI is essential for this role.