Generative AI & LLM Applications

Course overview

A practical, project-based programme for developers, data professionals and technology practitioners who want to move beyond using AI chatbots and learn how to build real-world Generative AI applications. Students explore how large language models work, develop reliable prompts, work with embeddings and vector databases, build Retrieval-Augmented Generation systems, integrate APIs, implement AI agents and apply evaluation, security and deployment practices.

Who it's for: Software developers, data analysts, data scientists, AI enthusiasts, product professionals and technology practitioners who want to build and deploy Generative AI applications.

What you will learn

• Understand the fundamentals of Generative AI and large language models
• Understand tokens, context windows, inference and model limitations
• Select appropriate AI models based on performance, cost and use case
• Design reliable and structured prompts for different business tasks
• Use few-shot prompting and structured output techniques
• Integrate LLM APIs into applications
• Work with embeddings and vector databases
• Build Retrieval-Augmented Generation applications
• Connect LLMs to private documents and knowledge bases
• Build AI-powered assistants and agentic workflows
• Implement evaluation, guardrails and responsible AI practices
• Optimise AI applications for cost, latency and reliability
• Deploy a production-ready Generative AI application

Curriculum

Prerequisites

• • Basic programming knowledge
• • Basic Python knowledge is recommended
• • Basic understanding of APIs is helpful but not required