Developing and executing test plans for the exploration of a variety of features, implementing automated tests for agentic AI flows.
Analysis of functional and non-functional requirements. Validate end-to-end AI-driven design and verification workflows across RTL generation, testbench creation, regression, debugging, and auto-fix loops.
Collaborate with R&D to define validation strategies and quality metrics.
Reproduce, isolate, and root-cause complex cross-domain bugs.
Provide actionable feedback to product and R&D teams to improve agent intelligence, robustness, and user experience.
Validate cloud and on-prem deployments, ensuring scalability, security, and reproducibility of AI workflows.
Participate in early customer evaluations by validating real customer deployments
Help junior engineers, conducting technical leadership inside projects.