Training course · RAG & LLM Applications · Data Science & Machine Learning

RAG & LLM Applications for Data Scientists and ML Engineers

Develop RAG and LLM applications: embeddings, vector databases, chunking, retrieval, evaluation, cost control and data protection.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

This course connects RAG & LLM Applications with the everyday processes of Data Science & Machine Learning. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

Retrieval-augmented generation connects language models to your own knowledge: manuals, contracts, tickets, wikis or product data are made searchable and handed to the model as context at runtime. The result is assistants that give grounded answers with citations instead of hallucinating. In this two-day course you build a complete RAG pipeline, from document preparation through embeddings and a vector database to answer generation, and you learn which levers actually determine quality.

Day two takes you from prototype to robust application. You compare chunking strategies, combine semantic and lexical search, apply reranking, metadata filters and query rewriting, and measure the effect with systematic evaluations. You also cover prompt caching, cost control, latency optimisation, document-level access control and privacy-compliant operation with an eye on GDPR and the EU AI Act. By the end you know when classic RAG is enough, when a large context window or agentic retrieval is the better option, and how to justify your architecture choices.

Data science and machine learning thrive on moving quickly between exploration, modelling and production. A great deal of time goes into data preparation with pandas or Polars, feature engineering, visualisation, hyperparameter experiments and finally turning notebook code into maintainable pipelines. AI coding assistants and agents speed up every one of these steps: they write exploration and plotting code, suggest validation strategies, refactor notebooks into tested Python modules, build scikit-learn or PyTorch training scripts and set up experiment tracking with MLflow. Methodological rigour is essential, though, because plausible-looking code can hide data leakage or misleading metrics. This course teaches you to use AI productively while safeguarding the statistical quality of your results.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • Data scientists in business units and analytics teams
  • ML engineers responsible for training and deployment
  • Data analysts moving into Python and machine learning
  • Researchers and developers with notebook-heavy workflows
  • MLOps teams running models in production

Typical challenges we address

  • Messy notebooks that are hard to reproduce and put into production
  • Time-consuming data preparation and feature engineering
  • Methodological pitfalls such as data leakage, unsuitable metrics or flawed validation
  • Lack of traceability for experiments, models and data versions

What you will be able to do

  • You build a complete RAG pipeline from document preparation to answers with citations.
  • You choose embedding model, chunking strategy and vector database on solid grounds.
  • You improve retrieval quality with hybrid search, reranking and metadata filters.
  • You measure application quality with systematic evaluations and detect regressions.
  • Accelerate exploration, feature engineering and modelling with AI assistants without sacrificing methodological rigour.
  • Use AI agents to turn notebook code into tested, reproducible ML pipelines.
  • Recognise typical errors in generated ML code, such as data leakage or unsuitable metrics, and correct them deliberately.

Course outline

Day 1

Module 1 Foundations of RAG and LLM applications
  • Anatomy of a RAG pipeline: ingestion, indexing, retrieval, generation
  • Understanding embeddings: semantic similarity, dimensions, model selection
  • Weighing RAG against fine-tuning and long context windows
  • Structured outputs, citations and dealing with hallucinations
Module 2 Document preparation and chunking
  • Reliably extracting PDFs, Office documents, HTML and tables
  • Chunking strategies: fixed size, structure-aware, semantic, with overlap
  • Enriching metadata and generating contextual summaries per chunk
  • Incremental updates and deletion of documents in the index
Module 3 Vector databases and retrieval strategies
  • Comparing vector databases and extensions such as pgvector, Qdrant, Weaviate or OpenSearch
  • Hybrid search combining vector and full-text search with BM25
  • Reranking, metadata filtering and query rewriting
  • Agentic retrieval: letting the model decide on search steps and tools
Module 4 Evaluation and quality assurance
  • Building and maintaining test sets from real user questions
  • Retrieval metrics such as recall and precision, and answer metrics such as faithfulness
  • Using and calibrating LLM-as-a-judge sensibly
  • Regression testing when chunking, model or prompt changes

Day 2

Module 5 Operations, cost and data protection
  • Prompt caching, batch processing and model choice to cut costs
  • Optimising latency and streaming responses
  • Document-level permissions, tenant isolation and protection against prompt injection
  • Data protection: data residency, processing agreements, deletion policies, GDPR and the EU AI Act
Module 6 Practice lab: Data Science & Machine Learning
  • Exploratory data analysis
  • Turning notebooks into pipelines
  • Model training and validation
  • Experiment tracking and MLOps
  • Explaining and auditing models
  • Evaluating LLM and RAG prototypes
Module 7 Data protection, quality & transfer to daily work
  • Training and analysis data often contains personal information, so use schemas, aggregates or synthetic data in prompts and observe GDPR principles such as purpose limitation. For high-risk applications, the EU AI Act sets requirements on data quality, documentation and transparency, and the licences of datasets, pre-trained models and Python packages must also be checked.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Exploratory data analysis

The assistant writes code for data profiles, distributions, correlations and missing values with pandas or Polars, produces meaningful visualisations and summarises anomalies as hypotheses for modelling.

Turning notebooks into pipelines

The agent refactors notebook code into Python modules with functions, configuration and pytest tests, removes hidden state and makes training and inference reproducible. Results become reliably comparable.

Model training and validation

The AI builds scikit-learn pipelines or PyTorch training loops with proper cross-validation, suitable metrics and baselines, and actively flags risks such as data leakage or class imbalance.

Experiment tracking and MLOps

The assistant sets up MLflow or similar tools for parameters, metrics and artefacts, versions models and creates training and deployment workflows for the CI/CD pipeline.

Explaining and auditing models

Using SHAP, permutation importance or partial dependence plots, the AI produces explanations of model decisions as well as analyses of fairness and robustness across relevant subgroups.

Evaluating LLM and RAG prototypes

The AI helps build evaluation datasets, automated scoring metrics and comparison experiments for prompt variants, embedding models or retrieval strategies. Quality, cost and latency of variants can be compared objectively.

Possible hands-on projects

Churn prediction with explanations

A complete project from data preparation through a gradient boosting model to a small Streamlit app displaying predictions and SHAP explanations.

Model monitoring script

A script that compares data and prediction distributions over time, detects drift and produces a compact report with charts. The team is notified automatically when anomalies appear.

Evaluation harness for a RAG chatbot

A test set-up with a question set, reference answers and automated scoring that compares different retrieval and prompt configurations. Results are summarised per configuration in a clear table.

Prerequisites

Solid programming skills in Python (or TypeScript as an alternative), basic knowledge of databases and REST APIs, and some experience with LLM APIs. Good Python skills, experience with pandas or Polars and scikit-learn, and a grounding in statistics and machine learning.

Technical requirements

A laptop with Python, Git, Docker and a code editor, plus API access to at least one LLM and embedding provider. Credentials for the exercises can be provided if needed.

Data protection & compliance

Training and analysis data often contains personal information, so use schemas, aggregates or synthetic data in prompts and observe GDPR principles such as purpose limitation. For high-risk applications, the EU AI Act sets requirements on data quality, documentation and transparency, and the licences of datasets, pre-trained models and Python packages must also be checked.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Mon, 23 November 2026 – Tue, 24 November 2026 Online Request
  • Thu, 3 December 2026 – Fri, 4 December 2026 Kaiserslautern Request
  • Wed, 9 December 2026 – Thu, 10 December 2026 Online Request
  • Mon, 14 December 2026 – Tue, 15 December 2026 Bremen Request
  • Wed, 13 January 2027 – Thu, 14 January 2027 Online Request
  • Wed, 20 January 2027 – Thu, 21 January 2027 Salzburg Request

Frequently asked questions

When is RAG better than fine-tuning?

RAG is the right choice when a model needs access to current, extensive or frequently changing knowledge and should cite its sources. Fine-tuning mainly changes style, format or specialised behaviour. In many projects RAG is the faster, cheaper and more controllable route, sometimes complemented by fine-tuning for niche tasks.

Which vector database should we use?

That depends on data volume, existing infrastructure, filtering needs and operating model. If you already run PostgreSQL, pgvector often takes you a long way, while specialised systems shine with large datasets and hybrid search. In the course you compare several options hands-on and derive criteria for your own decision.

How can RAG be run in a GDPR-compliant way?

Key factors are choosing providers with suitable data residency and a data processing agreement, enforcing document-level permissions, having a deletion policy for the index and logs, and minimising personal data. For highly sensitive data, self-hosted models are also an option. We work through these choices using realistic architectures.

Can I trust AI on statistical questions?

AI assistants know common methods very well but occasionally make methodological mistakes, for example in splitting training and test data or choosing metrics. On the course you learn to ask the AI explicitly about assumptions and risks, check results against baselines and sanity checks, and keep professional accountability firmly with yourself.

Does AI-assisted coding work in Jupyter notebooks?

Yes. Many assistants support notebooks directly, and agents can also read, execute and convert notebooks into modules. We show when notebooks are ideal for exploration and how to make the transition to versioned, tested code efficiently with AI support. The two approaches complement each other.

How much does “RAG & LLM Applications for Data Scientists and ML Engineers” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for Data Scientists and ML Engineers

More RAG & LLM Applications courses

All 29 RAG & LLM Applications courses

RAG & LLM Applications · MunichRAG & LLM Applications · SalzburgRAG & LLM Applications · BerlinRAG & LLM Applications · AugsburgRAG & LLM Applications · HanoverRAG & LLM Applications · BremenRAG & LLM Applications · StuttgartRAG & LLM Applications · KaiserslauternRAG & LLM Applications · Online