AI systems with their own data: LLM and Retrieval-Augmented Generation (RAG)
The practical boot camp for scalable RAG architectures with large language models
.svg)
Machine Learning Engineer
1. Introduction and basics
- Objectives, procedure, and alignment of expectations
- Value creation through generative AI in companies
- Classification of RAG in modern AI architectures
- Typical RAG use cases and limitations
2. Fundamentals of Retrieval-Augmented Generation
- Functionality and architecture of RAG systems
- Interplay between data, retrieval, and generation
- Common sources of error and quality issues
- Examples and best practices from real projects
3. Chunking and embeddings in practice
- Intuitive understanding of embeddings
- Chunking strategies and their effects
- Visualization of similarities in embedding space
- Hands-on implementation in Python notebooks
4. Retrieval, reranking, and generation
- Similarity Search and Top-K Retrieval
- Reranking strategies for better results
- Prompt design for RAG-based responses
- Implementation of a complete retrieval pipeline
5. Evaluation and optimization
- Why evaluating RAG systems is not trivial
- Quality metrics and automatic evaluation
- Systematic optimization of pipelines
- Comparison, parameter tuning, and traceability
6. Production deployment and MLOps
- Systematic optimization of RAG pipelines
- Parameter search, comparison, and traceability
- Experiment tracking & versioning (e.g., with MLflow)
- Implementation as a service with APIs and monitoring
- Deployment with FastAPI
7. Monitoring and drift
- Why RAG systems deteriorate over time
- Types of drift and their effects
- Practical drift analysis with modified data set
- Derivation of measures
In your online learning environment, you will find useful information, downloads and extra services for this training course once you have registered.
You will develop a deep, practical understanding of RAG-based AI systems and learn how they are technically structured.
You build complete end-to-end RAG pipelines yourself —from the data source to the productive API.
You will learn to critically evaluate RAG systems and systematically improve them, rather than just experimenting.
You understand how MLOps concepts are applied to LLM systems, including monitoring and drift analysis.
You will receive a practical blueprint that you can use to confidently transfer your own RAG solutions into the corporate context.
Thistraining conducted in a group of up to 12 participantsusing the Zoom video conferencing software.
You will mainly work in interactive Jupyter Notebooks with complete sample code.
Practical hands-on exercises guide you step by step through the process of setting up a RAG pipeline.
Typical problems and misconceptions are analyzed and solved using realistic use cases.
Discussions and reflection support the transfer to your own work context.
You will have space for your questions—individual support from the trainers guaranteed.
This bootcamp is aimed at developers, ML engineers, data scientists, solution architects, andconsultants who want to understand, build, and operate RAG systems.
Good Python skills are required. Basic knowledge of machine learning or NLP is helpful but not essential. The course is particularly suitable for anyone who wants to move from prototypes to robust, production-ready AI solutions.
.svg)
