---
title: "AI engineering"
description: "AI engineering fundamentals for builders: what AI engineers do, the skills and stack behind LLM applications, and a practical roadmap to become one."
type: "topic-hub"
canonical_url: "https://theaiengineering.com/topics/ai-engineering"
markdown_url: "https://theaiengineering.com/topics/ai-engineering.md"
author: "The AI Engineering Editors"
publisher: "The AI Engineering"
keywords: ["ai engineering","what is ai engineering","ai engineer","ai engineer roadmap","how to become an ai engineer"]
citation: "The AI Engineering Editors. \"AI engineering.\" The AI Engineering. https://theaiengineering.com/topics/ai-engineering"
---

# AI engineering

What AI engineers build, the stack they build it on, and how to learn it.

AI engineering is the discipline of building reliable products on top of foundation models. It sits between machine learning and software engineering: most AI engineers adapt pretrained models through prompts, context, retrieval, tools and evaluation rather than training models from scratch.

This hub collects the fundamentals: how large language models behave, the vocabulary of tokens and context windows, and a staged roadmap for engineers moving into the field. Every concept links to the deeper guides in the other hubs.

## AI engineering guides

- [AI engineer roadmap: skills, projects, and resources by stage](https://theaiengineering.com/articles/ai-engineer-roadmap): A practical AI engineer roadmap in seven stages, each with the skills to learn, a project to ship, and resources worth the time, from Python to production.
- [What is AI engineering? The discipline, the stack, and the work](https://theaiengineering.com/articles/what-is-ai-engineering): What is AI engineering? A plain definition, how it differs from ML and software engineering, the layers of the stack, and what AI engineers do day to day.

## Key terms

- [Context window](https://theaiengineering.com/glossary/context-window): A context window is the maximum number of tokens a language model can take into account in a single request, including the system prompt, conversation history, tool results, and the generated output.
- [Foundation model](https://theaiengineering.com/glossary/foundation-model): A foundation model is a large AI model trained on broad data, usually with self-supervised learning at scale, that can be adapted through prompting or fine-tuning to a wide range of downstream tasks.
- [Temperature](https://theaiengineering.com/glossary/temperature): Temperature is a sampling parameter that rescales a language model's next-token probabilities: low values concentrate probability on the likeliest tokens, and high values flatten the distribution for more varied output.
- [Tokens](https://theaiengineering.com/glossary/tokens): Tokens are the units of text a language model processes, typically whole words, word fragments, punctuation, or bytes, each mapped to an integer ID from the model's fixed vocabulary.

## Tools and platforms

- [Model providers](https://theaiengineering.com/platforms/model-providers): 38 platforms. A model provider is a company or research lab that trains large language models and makes them available through a hosted API, downloadable open weights, or both.

## Cite this page

The AI Engineering Editors. "AI engineering." The AI Engineering. https://theaiengineering.com/topics/ai-engineering

- Title: AI engineering
- Author: The AI Engineering Editors
- Publisher: The AI Engineering
- URL: https://theaiengineering.com/topics/ai-engineering
- Markdown: https://theaiengineering.com/topics/ai-engineering.md
