New opportunity

Senior Solutions Architect, Generative AI Deployment and AIOps

NVIDIA · Santa Clara, United States

About this role

Trusted technical advisor role focused on inference for Generative AI and Large Language Models (LLMs), working with customers and internal teams on performance analysis, modeling, and MLOps solutions. Requires experience analyzing AI inference workloads on Kubernetes and strong background with PyTorch, TensorFlow, Python, GPU/MIG management, containerization, and NVIDIA software.

Skills for this role

Generative AILarge Language Models (LLMs)Deep LearningAccelerated ComputingPyTorchTensorFlowPythonGPU orchestrationMulti-Instance GPU (MIG)KubernetesContainerizationOrchestrationMonitoringObservabilityLLM inferenceDL inferenceMLOpsNVIDIA GPUsNVIDIA NIMDynamoTensorRTTensorRT-LLMC++CDebuggingProfilingCode optimizationPerformance analysisTest designParallel programming''Distributed computing''Presentation skills''Communicati