Staff Software Engineer, Test & Validation – AI Kernels

At d-Matrix, we are focused on unleashing the potential of generative AI to power the transformation of technology. We are at the forefront of software and hardware innovation, pushing the boundaries of what is possible. Our culture is one of respect and collaboration. We value humility and believe in direct communication. Our team is inclusive, and our differing perspectives allow for better solutions. We are seeking individuals passionate about tackling challenges and are driven by execution. Ready to come find your playground? Together, we can help shape the endless possibilities of AI. Location: Hybrid—Santa Clara, CA headquarters, 3–5 days/week onsite Team: Kernels | Reports to: Engineering Manager, Kernels Cross-functional interface: QA / Test Engineering ABOUT THE ROLE We are looking for a Staff Software Engineer, Test & Validation – AI Kernels to embed within our Kernels team and own the quality engineering function for our AI compute software stack. You will design and build the test infrastructure, validation frameworks, and automated verification pipelines that ensure correctness, performance, and reliability of software kernels running on next-generation AI hardware. You will serve as the primary quality interface between the Kernels team and the broader QA organization, driving alignment on test strategy, coverage, and release readiness. This is a high-impact, deeply technical role that requires both strong software engineering skills and a rigorous quality mindset. You will work alongside compiler engineers, ML software engineers, and hardware architects while partnering closely with QA leads to define standards and share best practices across the company. WHAT YOU WILL DO TEST INFRASTRUCTURE & AUTOMATION - Design, build, and maintain scalable automated test frameworks for kernel validation across simulation, emulation, and silicon targets. - Develop correctness and performance regression suites covering ML operators (GEMMs, convolutions, BLAS, SIMD op