Module 1: Generative AI & LLM Fundamentals
- Understand what Generative AI is and how it differs from traditional ML
- Learn the basics of large language models (LLMs) and diffusion models
- Explore common GenAI use cases in business and products
Module 2: Data, Prompts & Responsible AI
- Learn how data quality impacts Generative AI outputs
- Practice prompt design and prompt engineering patterns
- Understand responsible AI, bias, safety, and governance
Module 3: Working with Pre‑Trained LLMs
- Use hosted LLMs via simple APIs and SDKs
- Build text generation, summarization, and Q&A workflows
- Evaluate and refine outputs for accuracy and usefulness
Module 4: Retrieval‑Augmented Generation (RAG)
- Combine your own data with LLMs using retrieval techniques
- Design a basic RAG pipeline (ingestion, indexing, retrieval, generation)
- Build a simple internal knowledge assistant or chatbot
Module 5: Image & Multimodal Generation
- Explore image generation models and common tools
- Create images from text prompts and refine styles
- Understand multimodal models that work with text, images, and more
Module 6: Building GenAI Applications
- Design end‑to‑end GenAI app flows (inputs, outputs, feedback loops)
- Integrate GenAI into web or backend applications
- Add guardrails, validation, and human‑in‑the‑loop review
Module 7: Optimization, Evaluation & Monitoring
- Measure quality with human and automated evaluation methods
- Optimize prompts, parameters, and workflows for cost and latency
- Monitor usage, drift, and user feedback over time
Module 8: Real‑World Projects & Capstone
- Design and build a real GenAI solution for a chosen use case
- Document architecture, risks, and mitigation strategies
- Present and get feedback on your capstone project
By the end of this program, learners will be able to design, build, and evaluate practical Generative AI applications using modern LLM and image generation tools.