CloudTeam

Main menu

Contact

TrainingDevelopment & DevOps / Programming & testingNVIDIA-RAGPROD

NVIDIA-RAGPRODNVIDIA · authorised training

NVIDIA: Introduction to Deploying RAG Pipelines for Production at Scale (English)

This training shows how to set up and manage scalable, production-ready Retrieval-Augmented Generation (RAG) pipelines using Kubernetes, NVIDIA NIMs, Helm, Prometheus, and Grafana. The training is practical and interactive, with hands-on work in a Kubernetes cluster.

Duration
1 day
Level
Intermediate
Provider
NVIDIA
Topic
Development & DevOps / Programming & testing

Course outline

  • Introduction: production-ready RAG pipelines at scale
  • Core components: NVIDIA NIMs, Kubernetes, Helm, Prometheus, Grafana
  • Kubernetes setup: configuring the interactive learning environment and basic Kubernetes commands
  • Deployment: end-to-end deployment of a RAG pipeline with Helm and use of individual NIM services
  • Monitoring: applying DCGM, configuring Prometheus and Grafana for performance monitoring
  • Autoscaling: implementing horizontal autoscaling (HPA) based on custom metrics
  • Load testing: performing load tests and conducting performance analyses

Skills you will gain

  • Deploy RAG pipelines on Kubernetes using Helm and the NVIDIA NIM Operator
  • Use NVIDIA NIMs for scalable, containerized Large Language Models (LLMs) and embedding models
  • Connect, customize, extend, and autoscale application components
  • Monitor application performance with Prometheus and Grafana
  • Perform load testing and optimize RAG pipelines

Who should attend

  • Machine Learning Engineers who want to deploy RAG applications in production environments
  • AI developers who want to implement scalable AI services
  • DevOps Engineers who manage Kubernetes environments running AI workloads
  • Software Architects who design robust AI architectures
  • Technical Leads who want to scale Proof-of-Concepts to enterprise production systems

Prerequisites

  • Basic knowledge of Kubernetes and container orchestration
  • Experience with AI models and LLMs is a plus
  • Familiarity with Helm, Prometheus, and Grafana is helpful but not required

Upcoming dates

These sessions run online with LLPA partners. Times are shown in Polish time, and the language of delivery is listed for each date.

DateTimes (Polish time)LanguageStatusPriceAction
09:30–16:30EnglishScheduled4330 PLNRequest a quote