This is a learning path for the introduction of the deployment and lifecycle of AI infrastructure. Explore the NVIDIA GPU Operator, a Kubernetes-native tool that automates driver installation, container runtimes, and device plugins. Perfect for DevOps engineers aiming to streamline high-performance, GPU-accelerated clusters at scale.

This learning path covers vector search from concept to practice. Articles explain vectors, embeddings, similarity metrics, and vector store software — including how to choose the right database and index type. The hands-on lab then stress-tests embedding models, compares distance metrics, evaluates models of different sizes, and builds a framework for tuning chunking and measuring retrieval quality.

RAG, or Retrieval-Augmented Generation, is an AI solution that combines the power of Generative AI with external data sources to provide more accurate and up-to-date responses. This Learning Path explains the concept of RAG, its origins, and how it addresses key limitations of traditional GenAI systems. You'll learn about the benefits of RAG, including enhanced accuracy, reduced hallucinations, and its flexibility in integrating real-time information without the need for constant model retraining.

Introduces LLM routing as a pattern for avoiding one-size-fits-all model usage, covering cost-based, complexity-based, and latency-based routing strategies and when adopting a router is (and isn't) worth it.