Developing and Deploying AI/ML Applications on Red Hat OpenShift A

Course ID : AI267

Duration In-class (в days) : 5 days

Duration Online : 5 days

Сurriculum : in-class, Virtual Instructor-Led Training - ONLINE

Overview

Operationalize the complete life cycle of modern AI applications at scale by using Red Hat OpenShift AI.

Developing and Deploying AI/ML Applications on Red Hat OpenShift AI (AI267) provides students with the fundamental knowledge to manage the complete life cycle of modern AI applications. This course helps students build core skills for using Red Hat OpenShift AI to efficiently train, test, deploy, and monitor both predictive and generative AI models at scale.

This course is based on Red Hat OpenShift ® 4.20, and Red Hat OpenShift AI 3.3.

Audience for this course

  • Linux system administrators.
  • Machine learning engineers responsible for deploying, automating, and monitoring tasks throughout the MLOps and LLMOps lifecycle.
  • Data scientists who train, deploy, and monitor custom models using Red Hat OpenShift AI.

Objective

  • Defining OpenShift AI as a unified MLOps and GenAIOps platform and setting up data analytics projects for team collaboration.
  • Creating, configuring, and managing workflows for AI/ML development and connecting to data sources.
  • Preparing, deploying, and running models using the OpenShift AI Model Serving runtime.
  • Deploying generative and predictive AI models using OpenVINO and vLLM.
  • Monitoring deployed models for bias, data drift, and performance metrics using TrustyAI.
  • Creating and managing data pipelines using Elyra and the Kubeflow Pipelines SDK.
  • Implementing advanced data pipeline features, including container components, artifact management, and experiment tracking.
  • Selection and optimization and evaluation of large language models using the OpenShift AI model catalog and LMEval.
  • Create production-ready AI applications, including RAG and agent-based workflows with safeguards.

Prerequisites for this course

  • Basic understanding of machine learning principles and workflows.
  • Basic understanding of generative AI and large language models (LLM).
  • Basic experience with Git.
  • Experience developing in Python or completion of the “Programming in Python with Red Hat” course (AD141).

Outcomes

After completing the course, students will gain skills that will allow them to:

    • Manage the complete life cycle modern applications artificial intelligence, effectively teaching, testing, unfolding and tracking how predictive, so and generating models of artificial intelligence at scale.
    • Configure projects for collaborating with data, effective use environments workbench and assign specialized resources.
    • Prepare, Deploy and Serve Models with using specialized execution.
    • Automate working processes MLOps per account creation advanced pipelines processing data and creation ready for production solutions GenAI.

Outline

  1. Introduction to Red Hat OpenShift AI
    Identify how Red Hat OpenShift AI provides a complete MLOps and GenAIOps platform and how to use it to configure data science projects for team collaboration.
  2. Using Workbenches for AI/ML Development
    Use workbench environments for AI/ML development and connect them to data sources and stores.
  3. Fundamentals of Model Serving
    Prepare, deploy, and serve models by using OpenShift AI model serving capabilities.
  4. Serving Generative and Predictive AI Models
    Deploy and serve AI models with specific runtimes, including OpenVINO for predictive models and vLLM for large language models.
  5. Monitoring AI Models
    Monitor deployed models for bias, data drift, and performance by using TrustyAI and observability tools to ensure reliable and ethical AI performance in production. 
  6. Introduction to Data Science Pipelines
    Create and manage basic data science pipelines by using Elyra and Kubeflow SDK to automate fundamental AI/ML workflows.
  7. Advanced Kubeflow Pipelines Development and Experiments
    Implement advanced pipeline features including container components, artifacts management, Kubernetes configuration, and systematic experimentation for production MLOps workflows.
  8. GenAI Model Selection, Optimization, and Evaluation
    Systematically select, optimize, and evaluate large language models by using RHOAI’s model catalog, compression techniques, and evaluation frameworks.
  9. Building GenAI Applications
    Build production-ready GenAI applications by using industry patterns including RAG, agentic workflows, and trustworthy AI practices, and move beyond basic model serving to ship complete intelligent solutions.

Ask question