Generative AI & Prompt Engineering Course

• Exercises to identify GenAI Use Cases in Diverse Domains
• LLM Guardrails
• Responsible AI in Generative Applications
• Low Code No Code ML/AI Platforms
• Basic Prompting to Build AI Applications

Learning Outcomes: At the end of this module, you will be able to create your first generative AI application from concept to deployment, gain a comprehensive understanding of the end-to-end workflow and tools for building and deploying GenAI, and learn to integrate principles of Responsible and Trustworthy AI aspects in their designs.

• Tokenization Fundamentals and Byte Pair Encoding
• How does the GPT class of models Generate Text?
• Training GPT Models
• Speech Models
• Interacting with Trained Models

Learning Outcomes: At the end of this module, you will learn the core principles of generative text models, delving into tokenization, multi-head attention mechanisms, and training techniques while also gaining detailed insights into encoder and decoder transformer models, data preparation and hands-on coding for fine-tuning foundational text generation models.

• Stable Diffusion Fundamentals
• Image and Video Generation
• Tools for Generating Images

Learning Outcomes: At the end of this module, you will acquire a comprehensive understanding of the core concepts of generative vision models, delving into vision transformers, stable diffusion, and CLIP training procedures while also understanding foundational image and video generation models.

• LLMOps – Tools, Platforms (incl, but not limited to LangChain, OpenAI API)
• AWS Sage Maker, Kendra
• Cloud Computing Tools - AWS ML Tools, Google Cloud, IBM Watson

Learning Outcomes: At the end of this module, you will gain insights into LLMOPs with Low Code, No Code Platforms, developing comprehensive agentic workflows and end-to-end GEnAI solutions.

• Vector Data Base
• LangChain with RAG and LLM Agents
• Advanced Prompting Strategies (e.g., CoT, ReAct, DSP)

Learning Outcomes: At the end of this module, you will dive deep into advanced prompting strategies like Chain of Thought and ReAct styles, grasp the fundamentals of Retrieval Augmented Generation using vector databases and decoder-only transformer models, build a RAG system from scratch in a hands-on activity, and enhance their problem-solving skills with LLM Agents.