Design and optimize end-to-end AI inference and AI training solutions, with a primary emphasis on AI inference architecture, software stack integration, and production deployment of large-scale GPU cluster environments using NVIDIA software and platform technologies, including NVIDIA AI Enterprise, Dynamo, NIM, NVIDIA Infrastructure Controller (NICo), Mission Control, LPx, and emerging inference acceleration capabilities. Ideal candidates will bring experience designing, architecting, and supporting large-scale AI infrastructure solutions in customer-facing environments, including GPU cluster deployments, AI inference platforms, and integrated hardware and software solutions for enterprise, cloud, hyperscale, or data center customers.