AI+ Cloud Practitioner™

Course structure

Module 1: Cloud Fundamentals

• 1.1 Cloud Computing Models
• 1.2 Core Cloud Services
• 1.3 Identity & Access Management (IAM), Security & Compliance Basics
• 1.4 Billing, Cost Optimization, and Cloud Economics
• 1.5 Multi-cloud Concepts
• 1.6 Infrastructure as Code (IaC) Basics with Terraform
• 1.7 Use Cases
• 1.8 Case Studies
• 1.9 Hands-On Activity

Module 2: AI Fundamentals and Python Fundamentals

• 2.1 Introduction to Artificial Intelligence, Machine Learning Types
• 2.2 Neural Networks and Deep Learning Fundamentals
• 2.3 Python Programming
• 2.4 Essential Libraries
• 2.5 Mathematics for AI
• 2.6 Data Preprocessing, Exploration, and Visualization Techniques
• 2.7 Use Cases
• 2.8 Case Studies

Module 3: Data Engineering for AI

• 3.1 Data Collection, Storage, and Processing Pipelines (ETL/ELT)
• 3.2 Big Data Technologies
• 3.3 Data Lakes, Data Warehouses, and Feature Stores
• 3.4 Data Quality, Governance, Versioning, and Cataloging
• 3.5 Real-Time Data Streaming
• 3.6 Use Cases
• 3.7 Case Studies

Module 4: Cloud with AI

• 4.1 Managed AI/ML Platforms
• 4.2 Model Training, Deployment, and Inference on Cloud
• 4.3 Containerization with Docker and Orchestration with Kubernetes
• 4.4 Serverless AI Architectures
• 4.5 Scaling and Monitoring AI Workloads
• 4.6 Use Cases
• 4.7 Case Studies

Module 5: Generative AI and LLM Models

• 5.1 Transformer Architecture, Attention Mechanism, and Tokenization
• 5.2 Major LLM Families: GPT, Llama, Gemini, Claude, Mistral
• 5.3 Prompt Engineering Techniques
• 5.4 Generative Model Lifecycle
• 5.5 Multimodal Generative AI
• 5.6 Use Cases
• 5.7 Case Studies

Module 6: Cloud with Generative AI and LLM Models

• 6.1 Deploying and Hosting LLMs on Cloud Platforms
• 6.2 Inference Optimization Techniques
• 6.3 Integration with Cloud-Native Services
• 6.4 Cost Governance for GenAI Workloads
• 6.5 Hybrid and Edge Deployment Strategies
• 6.6 Use Cases
• 6.7 Case Studies

Module 7: AI Workloads on Cloud

• 7.1 MLOps Lifecycle and Best Practices
• 7.2 Experiment Tracking (MLflow), Model Versioning, and CI/CD Pipelines
• 7.3 Model Monitoring and Performance Drift Detection
• 7.4 Orchestration Tools: SageMaker Pipelines, Vertex AI Pipelines, Kubeflow
• 7.5 Use Cases
• 7.6 Case Studies

Module 8: Retrieval-Augmented Generation (RAG)

• 8.1 RAG Architecture and Components
• 8.2 Vector Databases and Embeddings
• 8.3 Advanced RAG Patterns
• 8.4 Evaluation Metrics for RAG Systems
• 8.5 Cloud-Native Vector Search Services
• 8.6 Use Cases
• 8.7 Case Studies

Module 9: Fine-Tuning and Optimization on Cloud

• 9.1 Full Fine-Tuning vs. Parameter-Efficient Fine-Tuning (PEFT)
• 9.2 Distributed Training and Hyperparameter Optimization
• 9.3 Model Compression, Distillation, and Quantization
• 9.4 Domain Adaptation and Continual Learning
• 9.5 Cloud Tools for Efficient Fine-Tuning
• 9.6 Use Cases
• 9.7 Case Studies

Module 10: Agentic AI on Cloud

• 10.1 AI Agents Fundamentals
• 10.2 Distributed Frameworks: LangGraph, CrewAI, AutoGen, Semantic Kernel
• 10.3 Multi-Agent Systems and Orchestration
• 10.4 Autonomous Workflows and Decision Engines
• 10.5 Cloud Deployment of Agentic Systems
• 10.6 Use Cases
• 10.7 Case Studies

Module 11: Evaluation, Monitoring, Security & Responsible AI

• 11.1 Comprehensive LLM and GenAI Evaluation Frameworks
• 11.2 Bias Detection, Fairness, and Explainability
• 11.3 Security Threats
• 11.4 Guardrails, Content Moderation, and Compliance (GDPR, SOC2)
• 11.5 Responsible AI Governance and Audit Practices
• 11.6 Use Cases
• 11.7 Case Studies

Module 12: Capstone Project

• 12.1 Problem Identification and Solution Planning
• 12.2 AI Model Development and Cloud Deployment
• 12.3 Deliverables

Optional Module: AI Agents for Cloud

• 1. What Are AI Agents?
• 2. Examples of AI Agents for Cloud Services
• 3. Significance of AI Agents in Cloud Services
• 4. Trends in AI Agents for Cloud Services
• 5. Importance of AI Agents
• 6. Types of AI Agents
• 7. Case Studies
• 8. Hands-On Activity