AI On-Prem Deployment Video Course

Disclosure: links to my video training products are affiliate links, meaning when you click the links and make a purchase I receive a commission – at no extra cost to you.

AI On-Prem Deployment Video Course

Skill level

Beginner/Intermediate.

Course Requirements

No prior course requirements. Basic familiarity with Linux, containers, or Kubernetes may be helpful, but is not essential.

Why Choose This AI On-Prem Deployment Course?

Generative AI is transforming how organizations work, but sending sensitive prompts and proprietary data to external cloud services is not always an option. This hands-on video course shows you how to deploy, optimize, and run GenAI on your own Linux and Kubernetes infrastructure. You’ll gain:

• Private GenAI deployment: Understand the building blocks of generative AI, choose appropriate large language models (LLMs), and run them locally for greater control over data, privacy, performance, and cost.
• Practical Linux skills: Configure GPU drivers, enable GPU support for containers, tune CPU and GPU inference, and run AI workloads on systems with or without dedicated GPUs.
• Inference server expertise: Deploy and configure popular inference technologies, including llama.cpp and vLLM, and provide an accessible user experience with Open WebUI.
• Private data integration: Learn how to add proprietary documents and organizational knowledge to local LLMs using Retrieval-Augmented Generation (RAG) and adapters.
• Kubernetes readiness: Deploy GenAI workloads on Kubernetes, configure storage and GPU support, expose inference services, and apply scaling and monitoring techniques.
• End-to-end experience: Complete a practical deployment that brings the entire workflow together—from selecting an LLM and running the inference engine to connecting a client, adding private data, and applying best practices.
• Real-world flexibility: Prepare GenAI environments for regulated organizations, restricted or air-gapped networks, low-connectivity locations, and other situations where cloud dependency is not appropriate.

Who is this AI On-Prem Deployment course for?

This course is designed for:

• IT professionals responsible for deploying private AI solutions.
• DevOps and platform engineers managing Linux or Kubernetes infrastructure.
• System administrators who want to host and operate LLMs locally.
• Cloud and infrastructure professionals evaluating alternatives to public AI services.
• Technical professionals who need to run GenAI in regulated, restricted, or low-connectivity environments.
• Anyone who wants practical experience deploying and optimizing LLMs on their own hardware.

Hands-On Learning Approach

This is a practical, demonstration-led video course. Throughout the course, you’ll work with Linux, containers, LLM runtimes, Open WebUI, RAG workflows, and Kubernetes.
 
Many lessons include hands-on labs and lab solutions so you can practise each new skill and compare your approach with the instructor’s recommended implementation.
 

You will get the best results if

You actively follow the demonstrations and complete the included labs. Experiment with different models, inference settings, hardware configurations, and deployment approaches as you progress.
 
Taking time to practise GPU and CPU optimization, test RAG workflows, and review the Kubernetes deployment examples will help you develop the confidence to design and operate practical on-premises GenAI solutions.
 

What You’ll Learn in This AI On-Prem Deployment Course

• Module 1: Generative AI Fundamentals
• Module 2: Key GenAI Components
• Module 3: Large Language Models
• Module 4: Reducing LLM System Requirements
• Module 5: Hosting Platforms Overview
• Module 6: Hosting GenAI on Linux
• Module 7: Running an Inference Server
• Module 8: Adding Data to an LLM
• Module 9: Using Retrieval-Augmented Generation
• Module 10: Hosting GenAI on Kubernetes and Red Hat
• Module 11: Running GenAI on Kubernetes
• Module 12: Bringing It All Together

Details content

For a detailed outline of this course, visit this page.

Sample training videos

To get an idea about the video lessons and teaching style, visit this page.

About this CompTIA Linux+ V8 – Cert Prep Video Course

AI On-Prem Deployment is a hands-on video course, providing a practical path to running generative AI on your own infrastructure, without depending on external AI services for every prompt or document.
 
You’ll learn how to deploy and optimize LLMs on Linux, configure GPU and CPU-based inference, integrate private data with RAG, and run production-oriented GenAI workloads on Kubernetes. By the end of the course, you’ll have the practical knowledge to build private, high-performance, and flexible AI environments for a wide range of organizational needs.
 
This course is available on InformIT and the O’Reilly learning platform. Click here to activate your 30-days free O’Reilly trial.

Purchasing

Your purchase and delivery of the course is processed and available via InformIT.

If you are purchasing training and your organization requires a Purchase Order (PO), please send your request to mail@sandervanvugt.nl.