GenAIOps Enablement with Red Hat AI Enterprise (AI501)

Experience the practices, culture, and tools that enable teams to reliably and efficiently build, deploy, and maintain GenAI applications in production.
GenAIOps Enablement with Red Hat AI Enterprise (AI501) is a five-day immersive enablement, delivered the Red Hat Way, to build the skills that teams need to articulate and deliver on their AI vision. While many AI training programs focus on a particular framework or technology, this course covers how the tools fit together in a full Generative AI Operations workflow, treating the AI-enabled application, not just the model, as the unit of delivery.
To achieve the learning objectives, participants should include multiple roles from across the organization. AI engineers, application developers, platform engineers, architects, and IT managers will gain experience working beyond their traditional silos. The daily routine simulates a real-world delivery team building an AI-powered application, where cross-functional teams learn how collaboration breeds innovation. Armed with shared experiences and best practices, the team can apply what it has learned to help the organization’s culture and mission succeed in the pursuit of generative AI initiatives.
This course is based on Red Hat AI Enterprise, including Red Hat OpenShift AI, as well as Red Hat OpenShift GitOps, Red Hat OpenShift Pipelines, and Generative AI models and open source libraries. This course takes you on an end-to-end journey of an AI-enabled application, from prompt experimentation to production deployment, while bringing different personas together to collaborate on a single platform seamlessly.

Understanding GenAI fundamentals, including tokens, context windows, and model behavior
Experimenting with prompts and evaluating your first AI-enabled application
Introducing an orchestration layer for standardized GenAI development
Implementing Retrieval Augmented Generation (RAG) for knowledge-enhanced applications
Building autonomous AI agents with tool-calling capabilities
Deploying AI safety guardrails and implementing GenAI security practices
Enabling observability with metrics, logging, and distributed tracing for GenAI systems
Exploring small language models and multi-modal capabilities
Optimizing models through quantization and compression techniques
Implementing Models as a Service (MaaS) for scalable AI infrastructure