“We needed a partner who understood both the technical depth of Azure OpenAI and the governance requirements of an enterprise.”
Enterprise Program Brief
Building RAG Agents With LLMs
This NVIDIA DLI course teaches teams how to design retrieval-augmented generation systems and bundle them into deliverable formats. It also explores advanced LLM composition techniques for internal reasoning, dialog management, and tooling.
Duration
8 hours
Level
Advanced
Format
Virtual, On-site, or Hybrid
Language
English
NVIDIA
Agentic LLM SystemsGrounding, tools, orchestration
NVIDIA RAG Agents
On this page
Ideal for
Audience Profile
Built for these roles
Built for practitioners who want to move from general LLM usage into retrieval-grounded and agentic system design for production-facing solutions.
Overview
Executive overview
Official NVIDIA DLI generative AI program focused on retrieval-augmented generation systems and agent-based LLM workflows.
Readiness
Prerequisites
- Introductory deep learning knowledge with comfort in PyTorch and transfer learning preferred.
- Intermediate Python experience including object-oriented programming and libraries.
Program Outcomes
Capabilities your teams will gain
Design and structure retrieval-augmented generation systems
Build more capable agent-style LLM workflows
Apply advanced composition patterns for tooling and dialog management
Improve readiness for enterprise RAG deployment and scaling
Curriculum
Curriculum roadmap
RAG system fundamentals
Agent and tool orchestration
Dialog and reasoning patterns
Deliverable system packaging
1Module 1
Design retrieval-grounded LLM systems
+
Module 1
Design retrieval-grounded LLM systems
Learn the foundations of retrieval-augmented generation systems and the decisions involved in building grounded, useful LLM solutions.
- RAG system fundamentals
- Dialog and reasoning patterns
2Module 2
Build agentic and tool-using workflows
+
Module 2
Build agentic and tool-using workflows
Use orchestration and packaging patterns to create more capable LLM agents that can interact with tools and deliver measurable outcomes.
- Agent and tool orchestration
- Deliverable system packaging
Delivery Models
Delivery models
Engagement Fit
Engagement fit
Enterprise Customization
Enterprise customization
Tailor this program to your organization's priorities: Directly supports enterprise GenAI adoption by helping teams build retrieval-based, tool-using LLM agents that can support real business workflows.
- •Use your enterprise knowledge or document workflow as the basis
- •Add governance and evaluation emphasis for regulated scenarios
- •Extend into deployment, serving, and operationalization decisions
Credentials
Certification & official source
Aligned to the official source referenced for this program.
View Official SourceResources
Program resources
Yes. Most enterprise clients prefer private delivery scoped to role mix, timezone, and rollout timeline. We align lab environments and scenarios to your tenant context where applicable.
Enterprise Proof
Trusted delivery outcomes
Retail & E-commerce
Representative Retail Analytics Team
Instead of treating reporting as a tooling issue alone, the work focused on consistency, governance, and shared delivery practices across analysts and engineering teams.
- Higher consistency in report design practices
- Improved collaboration between analysts and engineering teams
Healthcare
Representative Healthcare Product Team
The engagement helped product and engineering stakeholders move from interest in AI to clearer implementation choices, security expectations, and prototyping discipline.
- Stronger alignment between product and engineering teams
- Improved clarity on prototype-to-production requirements
Delivery Capability
Enterprise-grade instruction
MCT-led delivery
Programs led by Microsoft Certified Trainer practitioners
Enterprise program oversight
Founder-led specialist delivery with structured rollout planning
Global delivery
APAC · EMEA · Americas · Virtual & Onsite
Implementation-focused
Hands-on labs aligned to production scenarios
