Resources worth following as an AI engineer: what to read, and when
The Ship AI Engineer team · Published 2026-10-06
The first problem someone starting out in AI engineering hits isn't a lack of information but too much of it. Every day brings a new model announcement, a new tool, a new technique that "changes everything". Trying to follow all of it feels busy, but it usually ends with weeks going by without learning a single thing in depth.
This post isn't a long list. It's a handful of resources that genuinely help, and the stage of learning at which each adds the most. We have no connection to any of them; our criterion was simple: their authors actually build or measure these systems, and what they write will still be worth reading a year from now.
While the concepts are settling
In the first stage, the goal is a solid mental model that everything else will later be built on. These resources help most here.
StatQuest. Explains statistics and machine learning concepts simply but soundly. Ideal for the topics you'll meet once you start evaluating, such as precision, recall and what averages hide. If you're wondering how much maths you need, see this post of ours too.
Seeing Theory. A free resource that teaches probability and statistics with interactive visuals. A short but effective way to get an intuitive feel for why a language model works in probabilities.
While you're building
When you start building your first projects, what you need is to see what people who hit the same problems did.
Simon Willison. A developer who experiments with language models every day and writes up the results openly. On prompt injection in particular he's been one of the most consistent sources for a long time; he's also the one who named it. A blog to read regularly, in short sessions. We covered the basics of the subject in our security post.
Eugene Yan. Practical, measurement-driven writing on search, recommendation systems and language model applications. His posts collecting recurring architectural patterns such as evaluation, RAG and caching are worth keeping as a reference while you design a system.
Hamel Husain. Writing on language model evaluation and AI products from a practitioner's point of view. One of the most convincing voices on why evaluation belongs at the centre of a product. We explained how to build your first test set in our evaluation post.
While you're shipping the product
The difference between a demo and a system serving real users becomes clear at this stage.
Chip Huyen. Thorough writing on AI systems in production, evaluation, and how the components of an AI application fit together. Her post that moves step by step from a single model call to a full platform reads well as a checklist for spotting what's missing as you prepare to ship.
When you want to go deeper
Once you've built a basic product, you start wondering about the research behind some topics. These resources are for that curiosity.
Lilian Weng. Long, thorough posts that survey the research on topics like agents, hallucination, reinforcement learning and diffusion models. Each is a map of a subject; read them not in one sitting but while you're actually working on that subject.
Sebastian Raschka: Ahead of AI. For following model architectures, fine-tuning methods and the research agenda in an understandable way. His experiments measuring how LoRA settings affect results are worth reading before deciding to fine-tune.
The Gradient. AI research, essays and technical analysis. For anyone who wants a broader view of where the field is going, beyond the day-to-day work.
How should you read these?
Don't try to follow all of them at once. Pick one or two that fit the stage of learning you're at, and apply what you read to a project. Trying something a post describes in your own code, rather than reading it and closing the tab, is the only way to really learn it. Reading gives you knowledge; applying it gives you skill. You can see the order to learn things in in our roadmap post, and every concept in the free knowledge map.
Keep reading
2026-10-05
Being an engineer in the age of AI: code got cheap, structure didn't
Writing code has never been this fast. But code produced quickly amplifies whatever structure sits underneath it. Why engineering matters more today, not less, and where to go deeper.
2026-10-02
Shipping an AI application: spending caps, caching, monitoring and model changes
In an ordinary web app every request costs roughly the same. In an app with a language model inside, it doesn't. Capping cost when you ship, using caching safely, watching the right things, and being ready when the provider retires a model.
2026-09-30
An AI engineer portfolio: what a project that gets you hired looks like
A chatbot demo impresses nobody anymore. Six signs that make an AI project credible, five project ideas that each show a different skill, and a README someone can read in two minutes.
2026-09-27
Prompt injection and abuse: why the server has to be the single source of truth in an AI app
An application with a language model inside carries every security problem of an ordinary web app and adds new ones. Why prompt injection can't be fully prevented, how to limit the damage, protecting the endpoint, and why the model's output can't be trusted.
2026-09-23
Building your first test set for an LLM application: a guide to evaluation
You changed the prompt and the answers look better. Do they? Building a first test set, taking a baseline, seeing what the average hides, the limits of one model grading another, and watching the system once it's live.
2026-09-19
When should you fine-tune, and when is it a waste of time?
Training a model on your own data is an attractive idea. Most of the time it's the wrong tool. What fine-tuning teaches and what it doesn't, how it compares with prompting and RAG, data quality, leakage, LoRA, and licences on open models.
2026-09-14
7 questions to ask before you pick an AI engineering course
Seven questions worth asking before you spend money and months on an AI engineering course. A short answer to each, and the concrete sign you can check in the syllabus before you buy.
2026-09-09
AI with image and audio input: the costs and failures your tests don't show
Handing a model a photo or a recording isn't the same as sending text. Request size, unreadable images, sentences invented in silence, generation that takes seconds, and an image paid for again on every turn.
2026-09-04
When don't you need an agent? Building and stopping a tool-using system safely
"Agent" is today's most requested and most easily misbuilt thing. The difference between a fixed workflow and an agent, why tool descriptions are critical, how to stop the loop, and how to protect irreversible actions.
2026-08-31
Why does RAG give wrong answers? Most failures are in retrieval, not the model
When a system that answers from your documents says something wrong, the model is the first suspect. Most of the time the culprit is the chunk it was given. Finding where the failure is, containing invention, citing sources and measuring properly.
2026-08-26
How to become an AI engineer: a roadmap that builds products, not models
Most roadmaps in the search results describe a different job. What the AI engineers being hired today actually know, the order to learn it in, and what makes each stage "done".
2026-08-21
When do you actually need a vector database? A practical guide to embeddings
The first step people take after deciding to build semantic search is usually picking a vector database. Most of the time it's an early step. What an embedding is, what a similarity score doesn't tell you, and the real reasons to move to a database.
2026-08-17
Managing prompts like code: versions, templates, schemas and tests
A prompt that works in a chat window quietly breaks inside an application. Keeping prompts in the repository, separating user input from instructions, validating the answer against a schema, and shipping a change only after measuring it.
2026-08-12
Why LLM APIs break under real traffic: rate limits, retries and timeouts
Three errors you never saw in development arrive together in the first busy hour. Telling 429 from 5xx, retrying properly, setting timeouts, and keeping the product up when the provider goes down.
2026-08-07
Do you need maths to become an AI engineer?
The honest answers to the six questions that stop people before they start: maths, degrees, machine learning, Python, hardware and money. Short answers first, reasons after.
2026-08-07
An AI engineer is not a machine learning engineer
Search "how to become an AI engineer" and the first page teaches linear algebra, CNNs and training loops. That is a different job. Here is what the work actually is, and what you can skip.