This specialization teaches end-to-end LLM engineering—from prompt design and evaluation to fine-tuning workflows, model optimization, and retrieval-augmented generation (RAG). You’ll learn to build robust LLM applications with measurable quality, safer outputs, and cost-aware performance using modern tooling such as LangChain, Hugging Face, and LangGraph. By the end, you’ll be able to design production-ready LLM pipelines that combine prompting, adaptation, and retrieval for real-world use cases.
Übungsprojekt
You’ll complete hands-on projects including: building reusable prompt systems with automated evaluation, fine-tuning and deploying a model using modern training pipelines, and shipping a RAG application with optimized retrieval, citations, and monitoring-focused evaluation.
