AI Engineer Core Track: LLM Engineering, RAG, QLoRA, Agents

Ed Donner’s core track follows several language-model applications, moving from model access and multimodal tasks to retrieval, adaptation, and agents. It provides a broad engineering route for someone who wants to compare approaches within one curriculum. The project sequence is useful context for choosing a later specialization.

What you will learn

• Compare hosted and open model approaches
• Build retrieval-backed applications
• Explore parameter-efficient model adaptation
• Connect model calls and tools in agent workflows

Who this suits

Best suited to a learner comfortable reading Python and working with notebooks or a development environment. Allow independent project time beyond the recorded lessons; the advertised week-by-week schedule is a suggested structure.

Before you enroll

Model APIs, hosted compute, and optional services may add charges. Match code to the course repository and current dependencies. Treat a successful demonstration as a starting point for evaluation, especially when comparing generated answers or fine-tuned models.

Paid course access follows Udemy’s current purchase or subscription terms. Check regional pricing, plan inclusion, and completion-certificate conditions on the provider page.

Put it into practice

Build a small knowledge assistant over documents you can verify. Compare a plain prompt with retrieval using the same questions, and record accuracy, latency, and cost.

Source and review

This overview is based on the provider's published information, checked on 11 October 2026. It is an editorial assessment, not a claim that we completed the resource. Time filters are approximate study ranges; projects and exercises can take longer.

View the curriculum and current access options at Udemy.

How YellowCourse describes and checks learning resources.