719-298-4047info@force7training.com
Student Login
Force7 Training
FRCAWS-13AWS

Developing Generative AI Applications on AWS

Duration · 2 daysVirtual + In-PersonInstructor-Led

$1,350

Course Description

This intensive 2-day instructor-led course teaches developers, engineers, architects, and technical teams how to design, build, deploy, and optimize generative AI applications using Amazon Web Services (AWS). Students gain hands-on experience with foundation models, prompt engineering, Retrieval-Augmented Generation (RAG), AI orchestration, model deployment, and secure AI application development using AWS-native AI services.

The course combines lectures, demonstrations, architecture discussions, guided labs, and a capstone project focused on real-world generative AI implementation patterns.

— Be First in Line —

Register Your Interest

We're finalizing the schedule for Developing Generative AI Applications on AWS. Add your details below and we'll notify you the moment a session opens for registration — no payment or commitment required.

Audience Profile

This course is intended for:

  • Software Developers
  • Machine Learning Engineers
  • Cloud Engineers
  • Solutions Architects
  • Data Engineers
  • DevOps Engineers
  • Technical Product Teams

Prerequisites

Before enrolling, you should have:

  • Basic Python programming experience
  • Familiarity with APIs and cloud services
  • General understanding of machine learning concepts
  • Basic AWS foundational knowledge recommended

— What You'll Learn —

Learning Objectives

In this course, you will learn to:

  • 1Understand generative AI and foundation model concepts
  • 2Build generative AI applications using AWS services
  • 3Implement prompt engineering best practices
  • 4Develop Retrieval-Augmented Generation (RAG) solutions
  • 5Integrate vector databases and embeddings
  • 6Orchestrate AI workflows and APIs
  • 7Deploy secure and scalable generative AI applications
  • 8Monitor, govern, and optimize AI workloads
  • 9Design enterprise-ready AI architectures on AWS

— Day-by-Day —

Course Outline

Day 1 — Foundations of Generative AI on AWS

Module 1

Introduction to Generative AI and Foundation Models

Topics

  • Overview of generative AI
  • Large Language Models (LLMs)
  • Foundation model capabilities and limitations
  • Common enterprise use cases
  • Responsible AI and ethical considerations
  • AWS generative AI ecosystem overview
  • AWS Services Covered
  • Amazon Bedrock
  • Amazon SageMaker
  • AWS IAM
  • Amazon S3

Lab

  • Explore foundation models in Amazon Bedrock
  • Configure generative AI development environment
  • Test model inference APIs

Module 2

Prompt Engineering Fundamentals

Topics

  • Prompt design principles
  • Zero-shot and few-shot prompting
  • Chain-of-thought prompting
  • Prompt tuning techniques
  • Reducing hallucinations
  • AI response optimization strategies

Lab

  • Create and refine prompts
  • Compare outputs across foundation models
  • Optimize prompts for business use cases

Module 3

Building Generative AI Applications

Topics

  • Application architecture patterns
  • API-driven AI integration
  • Conversational AI design
  • Chatbot and assistant workflows
  • Serverless AI application patterns
  • AWS Services Covered
  • AWS Lambda
  • Amazon API Gateway
  • AWS Step Functions
  • Amazon CloudFront

Lab

  • Build a serverless AI chatbot
  • Create API integrations with foundation models
  • Implement conversational workflows

Module 4

Embeddings and Vector Databases

Topics

  • Semantic search concepts
  • Text embeddings
  • Vector similarity search
  • Knowledge retrieval patterns
  • Context-aware AI systems
  • AWS Services Covered
  • Amazon OpenSearch Service
  • Amazon Aurora PostgreSQL with pgvector
  • Amazon Bedrock Embeddings

Lab

  • Generate text embeddings
  • Build semantic search workflows
  • Store and query vectorized data

Day 2 — Advanced AI Architectures and Deployment

Module 5

Retrieval-Augmented Generation (RAG)

Topics

  • RAG architecture fundamentals
  • Document ingestion workflows
  • Knowledge base design
  • Context retrieval optimization
  • Enterprise search integration
  • AWS Services Covered
  • Amazon Bedrock Knowledge Bases
  • AWS Glue
  • Amazon S3
  • Amazon OpenSearch Service

Lab

  • Build a RAG-based application
  • Ingest enterprise documents
  • Implement contextual question-answering

Module 6

AI Orchestration and Workflow Automation

Topics

  • Multi-step AI workflows
  • AI agent concepts
  • Event-driven AI processing
  • Workflow orchestration patterns
  • Integrating external services and APIs
  • AWS Services Covered
  • AWS Step Functions
  • Amazon EventBridge
  • AWS Lambda

Lab

  • Build automated AI processing workflows
  • Create AI orchestration pipelines
  • Trigger event-driven AI tasks

Module 7

Security, Governance, and Responsible AI

Topics

  • AI security best practices
  • Identity and access management
  • Data privacy and compliance
  • Content filtering and moderation
  • Responsible AI governance frameworks
  • Monitoring model behavior
  • AWS Services Covered
  • AWS IAM
  • AWS KMS
  • Amazon CloudWatch
  • AWS CloudTrail

Lab

  • Configure AI application security
  • Implement logging and monitoring
  • Apply governance controls

Module 8

Deploying and Scaling Generative AI Applications

Topics

  • Production deployment strategies
  • Scalability and high availability
  • Cost optimization for AI workloads
  • Performance monitoring
  • Multi-region AI architectures
  • Operational best practices
  • AWS Services Covered
  • Amazon ECS
  • AWS Fargate
  • Elastic Load Balancing
  • Amazon CloudWatch

Lab

  • Deploy scalable AI applications
  • Configure monitoring dashboards
  • Optimize inference performance and cost

Module 9

Capstone Project

  • Student Project
  • Students design and implement a complete generative AI application on AWS.
  • Capstone Activities
  • Design application architecture
  • Build AI workflows using foundation models
  • Implement semantic search and RAG
  • Secure and monitor the environment
  • Present architecture and operational strategy
  • Included Hands-On Labs
  • Students complete guided labs covering:
  • Foundation model access
  • Prompt engineering
  • AI chatbot development
  • API integrations
  • Vector database implementation
  • Embedding generation
  • Retrieval-Augmented Generation (RAG)
  • Workflow orchestration
  • AI application security
  • Monitoring and optimization

— Additional Details —

What else is included

Suggested Course Materials

  • Student guide
  • Instructor presentation slides
  • Hands-on lab manual
  • AWS architecture diagrams
  • Sample datasets and documents
  • Capstone workbook

Note: Course outlines are provided as a general guide. Content, pacing, labs, and instructional emphasis may vary based on instructor expertise, student experience levels, and customer-specific learning objectives.

— Keep Exploring —

Need a different angle?

Browse the full AWS catalog or chat with an advisor about a custom training plan for your team.