Work with engineering, product, and solution architecture teams to understand the technical capabilities of NVIDIA’s AI infrastructure and inference stack, including accelerated compute, networking, CUDA libraries, model architectures, and deployment techniques. Familiarity with modern data center and accelerated computing concepts, deep learning frameworks (PyTorch, JAX), and inference serving and optimization approaches (TensorRT-LLM, vLLM, SGLang, Triton Inference Server, or similar).