.svg)
.svg)
.svg)
Machine Learning Engineer
1. technical basics of generative language models
- The evolution of chatbots into LLM agents
- Text embeddings: From text to vectors
- Efficient language modeling with the Transformer architecture
- How modern chat models work
- Evaluation of language models
2. LLMs via API and cloud integration
- Use proprietary APIs (OpenAI, Anthropic, Google AI)
- LLMs in the cloud (Azure OpenAI Service and others)
- Security, data protection, cost control for API calls
3. use open source language models
- Host open source language models yourself
- Easy access to open source LLMs using the example of Ollama
- Building your own AI chat application with OpenWebUI and Ollama
4. best practices in LLM development
- Use LLM frameworks: LangChain, LlamaIndex, Haystack and others.
- Generate structured data with LLMs
- Structured JSON outputs and data extraction
5. customize LLM: RAG and fine tuning
- Basics: Retrieval Augmented Generation (RAG) in projects
- Construction of a simple RAG system with LlamaIndex
- When and how fine-tuning is used in relation to RAG
6. advanced concepts and practice
- Introduction to multimodal models (text & vision)
- Quantized models for limited memory requirements
- Agentic AI: using language models for complex tasks
- Practical project: Development of a chatbot (end-to-end)
Overview of models and technologies: You will gain an overview and detailed knowledge of the different approaches in the development of AI solutions - with open source or proprietary models, via API or locally hosted, with fine-tuning or RAG, with or without cloud services.
Developing practice-ready assistants: After learning the basics and technology, you will develop an AI assistant yourself in practical exercises.
Make well-founded technology decisions: You compare public API, Azure OpenAI and own GPU clusters in terms of cost, latency and control.
Scale without surprises: Quantization, security measures and local hosting allow you to keep operating costs and risks under control.
Support for learning transfer: cloud lab, source code, Jupyter notebooks and deploy blueprint ensure transfer to your everyday work.
This training training is conducted in a group of a maximum of 12 participants using the Zoom video conferencing software.
In the training , you work in a cloud-based lab environment provided by the trainers . All you need is a web browser and an internet connection; no additional software needs to be installed.
Interactive Jupyter notebooks serve as learning material and working environment. You get access to source code, documentation, references and links. A powerful server for working with current AI models is provided.
The course is held in German, the course materials are mostly available in English due to the focus on programming.
There is room for your questions - individual support from the trainers is guaranteed.
You can access further materials in your personal learning environment.
developers developers, ML engineers, data scientists, solution architects and consultants consultants who want to design, implement and operate AI assistants.
Basic knowledge of Python is required, as examples are analyzed and programmed on a code basis. Existing data science knowledge is helpful, but not essential.
.svg)
