Advanced AI Engineering: LLMs, RAG and Agents

In this training, you'll gain practical insight into how modern AI systems are designed and built. You'll learn how to work with large language models (LLMs) like those used in ChatGPT and Copilot, how to combine context and knowledge using Retrieval-Augmented Generation (RAG), and how to build AI agents with specific behavior and domain knowledge. During hands-on sessions, you'll work with Python, prompt engineering, embeddings, vector databases, and multi-agent architectures,  applied in realistic assignments.

What you'll learn

• The fundamentals of neural networks and large language models (LLMs).
• Prompt engineering and context-driven interaction with AI and ChatGPT.
• Embeddings and vector databases for semantic search.
• Setting up and applying Retrieval-Augmented Generation (RAG).
• Building AI agents with custom instructions and knowledge sources.
• Designing multi-agent systems and applying best practices.

After this course you'll be able to:

• Design, test, and refine your own AI agents.
• Apply RAG models within your data or business environment.
• Use prompt strategies for more reliable and accurate results.
• Integrate AI into ETL processes and development workflows.

Who is this for

• Data scientists and data engineers.
• Python developers who want to integrate AI into their workflow.
• AI and ML professionals looking to deepen their knowledge towards production-ready AI applications.

Prerequisites

• Experience with Python.
• Basic knowledge of AI and machine learning concepts (such as LLMs, APIs, or model usage).

Programme

Day 1 – Introduction to AI and Agents

• Fundamentals of AI and language models like ChatGPT and Copilot.
• The concept of agents and their capabilities.
• Building your first agent in Python.

Day 2 – Multi-Agent Systems

• How agents collaborate on complex tasks.
• Designing and implementing multi-agent workflows.

Day 3 – Alternative Frameworks

• Working with frameworks such as LangChain and LangGraph.
• Building flexible and scalable agent architectures.

Day 4 – Implementation and Best Practices

• Deploying agents in ETL processes or development environments.
• Reliability, scalability, and performance optimization.

Day 5 – Case Study

• Developing an end-to-end case study.
• Designing and implementing an advanced AI agent solution.