Implementing Cisco Data Center AI Infrastructure

Overview

This course provides a comprehensive introduction to designing, implementing, operating, and troubleshooting AI-enabled data centre infrastructure using Cisco technologies. Learners will explore how artificial intelligence and machine learning workloads influence modern data centre design, networking, compute, and storage decisions.

The course focuses on the practical requirements of supporting AI workloads at scale, including high-performance networking, workload placement, security, sustainability, and day-two operations. Learners will examine how AI infrastructure is monitored and optimised using telemetry, analytics, and automation tools, alongside hands-on exposure to troubleshooting techniques for complex AI and machine learning environments.

Prerequisites

There are no formal prerequisites for this course. However, learners are expected to have prior knowledge of core data centre technologies and networking concepts.

Recommended knowledge includes an understanding of Cisco Unified Computing System architecture and operations, familiarity with Cisco Nexus switching technologies, and experience with data centre core networking principles. Learners who have previously studied Cisco data centre fundamentals or have hands-on operational experience will benefit most from this course.

Target audience

This course is designed for technical professionals responsible for designing, implementing, or supporting data centre infrastructure that enables AI and machine learning workloads.

Typical roles include network engineers, data centre engineers, systems engineers, storage administrators, technical architects, and consulting engineers. It is also suitable for technical leads and programme or project managers who require a deeper understanding of AI infrastructure requirements and operational considerations within modern data centres.

Objectives

By the end of this course, learners will be able to:

• Describe key artificial intelligence concepts, including traditional AI, machine learning, deep learning, and generative AI, and explain their impact on data centre infrastructure
• Explain how AI technologies enhance network operations through automation, predictive analytics, and anomaly detection
• Describe the architecture and operational principles of AI and machine learning clusters, including model acquisition, optimisation, and lifecycle management
• Identify the essential components required to build robust, scalable, and sustainable AI infrastructure
• Design and evaluate workload placement strategies to ensure performance, interoperability, and cost efficiency
• Explain the network requirements for AI workloads, including transport technologies, congestion management, and lossless fabric design
• Monitor, operate, and troubleshoot AI infrastructure using telemetry, analytics, and modern observability tools

Outline

Foundations of artificial intelligence

• Introduction to artificial intelligence concepts and terminology
• Traditional AI, machine learning, and deep learning techniques
• Overview of generative AI, its challenges, and emerging trends
• Common AI and machine learning use cases in data centre environments

AI clusters, models, and tooling

• Architecture and core components of AI and machine learning clusters
• Introduction to pre-trained models and fine-tuning approaches
• Using Jupyter-based environments to support AI-driven automation
• Applying generative AI tools to enhance operational productivity

AI infrastructure fundamentals

• Key infrastructure components required to support AI workloads
• Compute, networking, and storage considerations for AI environments
• Workload placement strategies and interoperability requirements
• AI-specific policies, governance frameworks, and compliance considerations
• Designing sustainable AI infrastructure with a focus on efficiency and cost optimisation

Networking for AI workloads

• Key network challenges introduced by AI and machine learning applications
• Transport technologies supporting AI workloads, including optical and copper connectivity
• Network connectivity models and architectural design patterns
• Layer 2 and Layer 3 protocols supporting distributed AI processing
• Migration strategies from traditional data centre networks to AI-optimised fabrics

High-performance Ethernet and lossless fabrics

• Overview of RDMA and RoCE mechanisms and operations
• Designing high-throughput, low-latency Ethernet fabrics
• Quality of service tools for lossless network design
• Understanding congestion management using ECN and PFC
• Monitoring congestion and performance using Cisco Nexus Dashboard Insights

Data preparation and performance considerations

• Introduction to data preparation processes for AI and machine learning
• Understanding how data performance impacts AI workload efficiency
• Monitoring AI and machine learning traffic flows
• Evaluating infrastructure behaviour across different AI workload stages

AI-enabling hardware and virtualisation

• AI-specific compute hardware and accelerators
• Compute resource architectures for AI workloads
• Virtual infrastructure options and deployment considerations
• Storage protocols, software-defined storage, and data access strategies

AI infrastructure deployment and operations

• Setting up and configuring AI clusters
• Using fabric management tools to optimise AI workloads
• Deploying and using locally hosted generative AI models with retrieval-augmented generation
• Operational monitoring of AI infrastructure components

Troubleshooting AI infrastructure

• Common issues in AI and machine learning fabrics
• Troubleshooting performance, connectivity, and congestion problems
• Using telemetry and analytics to diagnose infrastructure issues
• Applying structured troubleshooting methodologies in AI-enabled data centres

Exams and assessments

This course prepares learners for the Implementing Cisco Data Center AI Infrastructure 300-640 DCAI exam. The exam assesses knowledge of AI infrastructure design, implementation, monitoring, and troubleshooting within data centre environments.

There are no formal assessments during the course itself. Knowledge checks and practical exercises are used throughout the training to reinforce learning and prepare learners for the certification exam.

Hands-on learning

This course includes practical exercises designed to reinforce key concepts and support real-world application. Learners will work with AI infrastructure tooling to explore monitoring, configuration, and troubleshooting scenarios. Hands-on activities focus on applying theoretical knowledge to realistic data centre environments and operational challenges.