Advanced AI Engineering for Developers

In this training, you gain a practical understanding of how modern AI systems are designed and implemented. You learn how large language models (LLMs) work, how they combine context and knowledge via Retrieval-Augmented Generation (RAG), and how to create AI agents with specific behavior and domain knowledge. Through hands-on exercises, you work with prompt engineering, embeddings, vector databases and multi-agent architectures, and apply them to realistic scenarios.

What you learn

• The fundamentals of neural networks and large language models.

• Prompt engineering and context-driven interaction with AI.

• Embeddings and vector databases for semantic search and retrieval.

• Setting up and using Retrieval-Augmented Generation (RAG).

• Building AI agents with custom instructions and knowledge sources.

• Designing multi-agent systems and applying best practices for implementation.

After this course you will be able to:

• Design, test and refine your own AI agents.

• Apply RAG models within your own data or business environment.

• Use prompt strategies for more reliable and accurate outputs.

• Integrate AI components into ETL pipelines and development workflows.

For whom

• Data scientists.

• Data engineers.

• AI and ML professionals who want to move toward production-grade AI applications.

Prerequisites

• Experience with Python.

• Basic familiarity with AI and machine learning concepts (for example LLMs, APIs and model usage).

Content (global program)

Day 1 – Introduction to Agents

• Fundamentals of AI and language models.

• Concept of agents and capabilities.

• Building your first single agent.

Day 2 – Multi-Agent Systems

• How multiple agents collaborate on complex tasks.

• Designing and implementing multi-agent workflows.

Day 3 – Alternative Frameworks

• Exploring frameworks such as LangChain and LangGraph.

• Building flexible and scalable agent architectures.

Day 4 – Implementation and Best Practices

• Deploying and using agents in ETL and development environments.

• Best practices for reliability, scalability and performance.

Day 5 – Case Study

• End-to-end case study using all concepts from the week.

• Designing and implementing an advanced AI agent solution.