• Support customers in building scalable and observable GPU-accelerated pipelines for key robotics workloads using Kubernetes, cloud-native technologies, and NVIDIA frameworks (OSMO, Dynamo) across heterogeneous infrastructure. • Develop a deep understanding of robotics workloads scaling and help translate those into optimal architectures for partners • Collaborate with DevOps teams to orchestrate data preprocessing, distributed training and inference workloads to optimize job scheduling, costs, storage access, and networking across hybrid and multi-cloud Kubernetes environments (e.g., AWS, Azure, GCP, on-prem) • Accelerate inference pipelines using NVIDIA NIM, TensorRT-LLM, vLLM, SGLang, and other engines to enable seamless, disaggregated inference architectures. • Collaborate with multi-functional teams (business, engineering, product) and provide technical mentorship to customers implementing Physical AI at scale.