Mastering Generative AI From Neural Networks to Multi-Agents

Learn the fundamentals of LLMs, Transformers, AI Agents, Multi-Agents, RAG

What you'll learn
- Learn the fundamentals of Machine Learning, Deep Learning and Generative AI
- How to create, train and run Deep Neural Networks
- What are the building blocks of a LLM: Tokenization, Pre-Training, SFT and RLHF
- Customization strategies for LLMs with Fine-Tuning, RAG and Prompt Engineering
- Building AI Agents with ReAct and Strands SDK
- Fundamentals of NLP to classify documents, extract entities and intelligent document processing
- Using AI to edit and create images with Transformer based Models
- Create GenAI architectures with Amazon Bedrock
- Build AI Agents with Amazon Bedrock and Strands SDK
- Create Multi-Agentic Architectures and differentiate between Multi-Agent Topologies

Requirements
- No programming necessary you will be guided through all steps
- Python and Computer Science experience helpful
- You can run the course on your own laptop or on SageMaker Studio Labs (free) to lower hardware barrier

Description
Master Generative AI from the ground up in this comprehensive masterclass that takes you from core machine learning concepts to building production-ready AI applications. Whether you're a software engineer, data scientist, or tech professional looking to stay ahead of the AI revolution, this course provides everything you need to become a Generative AI expert.

Core Foundations:

Deep dive into Machine Learning, Neural Networks, and Deep Learning fundamentals

Understand embeddings, transformers, and diffusion models that power modern AI

Learn how foundation models like GPT, Claude, and Stable Diffusion actually work

Natural Language Processing Mastery:

Build and fine-tune Large Language Models (LLMs) for conversation and text generation

Master tokenization, text classification, topic modeling, and named entity recognition

Understand evaluation metrics and benchmarks used by industry leaders

Implement supervised fine-tuning for specialized AI applications

Image Generation & Computer Vision:

Create stunning images using text-to-image and image-to-image models

Master image editing, inpainting, and style transfer techniques

Fine-tune image generation models for custom use cases

Advanced Model Customization:

Master prompt engineering and in-context learning strategies

Build Retrieval Augmented Generation (RAG) systems that ground AI in your data

Implement cutting-edge GraphRAG and StructRAG architectures

Apply Parameter-Efficient Fine-Tuning (PEFT) and LoRA techniques

Train models using Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO)

Optimize models through knowledge distillation

Agentic AI & Advanced Orchestration:

Understand the fundamentals of AI agents and agentic reasoning

Master the ReAct (Reasoning and Acting) framework for tool-using agents

Design and implement multi-agent systems with role specialization

Build agent topologies: sequential, hierarchical, and collaborative patterns

Implement automatic handoffs and agent coordination strategies

Create agents that can plan, reason, and execute complex multi-step tasks

Hands-On Learning Experience

This isn't just theory—you'll build real AI applications through8 comprehensive labsthat progressively build your skills:

Lab 1: Neural Network Fundamentals & Transfer LearningBuild an image classifier from scratch, understand training and inference pipelines, and leverage transfer learning with ResNet for state-of-the-art performance.

Lab 2: AWS & Generative Image CreationSet up your AWS environment, work with Amazon Bedrock, and create and edit stunning images using Amazon Nova models—your gateway to cloud-based AI.

Lab 3: Embeddings & Vector SearchMaster embedding models with HuggingFace, build a production-ready RAG system, and implement efficient vector databases with IVF and HNSW indexing strategies.

Lab 4: Advanced LLM TechniquesWork with Amazon Bedrock LLMs for real-world tasks: prompt engineering, text classification, document summarization, and creative content generation.

Lab 5: Conversational AIBuild an intelligent chatbot using Amazon Bedrock and Gradio with memory management and multi-turn conversation capabilities.

Lab 6: Custom AI AgentsImplement your own ReAct (Reasoning and Acting) agent from scratch with Amazon Bedrock, understanding how agents think and use tools.

Lab 7: Full-Stack Agentic ApplicationCreate a production-ready agentic chatbot using the Strands SDK, FastAPI backend, and Amazon Bedrock—ready for real-world deployment.

Lab 8: Multi-Agent SystemsBuild sophisticated multi-agent systems with the Strands SDK featuring automatic handoffs, agent collaboration, and coordinated problem-solving.

Who this course is for:
- Tech and Business people interested to improve their career in AI space
- Students who want to learn the gist of GenAI and Agentic AI to succeed in career entry
- Software Developers, Machine Learning Engineers, Data Scientists
- Beginner in Cloud who want to learn using Amazon Bedrock and Strands SDK to build Agentic and GenAI solutions
More Info