Own the formal Deliverable Acceptance process for TOP's external vendor engagement, reviewing each submitted Deliverable against the Acceptance Criteria defined in the vendor SOW and issuing written acceptance or a specific, actionable defect list · Verify vendor container image deliverables against the Software Bill of Materials (SBOM), confirming that all declared components are present and no unapproved components are included · Validate that vendor-delivered AI engine deployments comply with the client’s technical architecture requirements, including confirming that fine-tuned model weights are stored in Vertex AI Model Registry and not embedded in container images · Design, build, and maintain automated test suites for TOP platform backend services, APIs, and data pipelines · Develop AI engine output evaluation frameworks that test inference quality against defined accuracy benchmarks for each dealer service use case · Own the UAT (User Acceptance Testing) process for dealer-facing interfaces, coordinating with Service stakeholders to recruit pilot users, design test scenarios, and capture structured feedback · Manage Jira project bug triage workflow: creating Bug records for confirmed Tier 2 issues, assigning priority in alignment with SLA tiers, tracking vendor acknowledgment and resolution timelines, and reporting SLA compliance metrics · Perform regression testing for each new container image version before the client authorizes production deployment · Define test environments within client's GCP project space in collaboration with the GCP Cloud Engineer, ensuring test environments accurately reflect production configurations · Produce quality metrics reports for program leadership covering defect rates, SLA compliance, and test coverage across all TOP platform components. Experience Preferred: Experience evaluating LLM or AI model outputs for production quality, including prompt regression testing and AI output consistency validation · Familiarity with Dynatrace or equivalent APM (Application Performance Monitoring) tooling for test environment monitoring · Experience in automotive or manufacturing quality contexts where structured acceptance processes are the norm · ISTQB certification or equivalent formal QA training · Experience with performance and load testing for cloud-native APIs serving high-volume, real-time workloads.