Generative AI Engineer Interview Guide

How LLMs work, prompting and context, fine-tuning versus RAG, and keeping cost and latency in check.

Email me the free PDF or read the questions now

Free PDF · sent by email the day it’s ready

Who it’s for

For engineers interviewing for roles built around LLMs: generative AI engineer, LLM engineer, applied AI engineer.

Most questions are about the model itself and how you shape its output.

What it covers

How LLMs work
Prompting and context
Fine-tuning vs RAG
Cost and latency

A question from the guide

One of the 50 questions, with its model answer.

Fundamentals

What happens, step by step, when you send a prompt to an LLM?

Model answer

The API wraps my messages in the model's chat template, so system prompt, history and my message become one long sequence of text. That text is tokenized into IDs, each ID is looked up as an embedding vector, and the vectors go through a stack of transformer layers. At the last position the model outputs a logit for every token in its vocabulary, softmax turns those into probabilities, and a sampler picks one token. That token is appended and the whole thing runs again, one token at a time, until a stop token or the max-token limit. Processing the prompt is called prefill and it's why there's a pause before the first token; the token-by-token part is decode, which is what you see streaming. And the model keeps nothing between calls: anything it seems to remember was sent again in the context.

What they’re checking:: Whether you have a working mental model of tokenize, embed, transform, predict, sample and repeat, and know the model is stateless.
Likely follow-up:: Where in that pipeline does the randomness come from, and why does the response pause before it starts streaming?

See all 50 questions: 50 LLM Interview Questions and Answers →

What the guide will include

Questions by round
The questions for each part of the loop, grouped the way the interview usually moves.
Answers you can say out loud
Each model answer runs about a minute spoken: the answer first, one example, one tradeoff.
What they’re checking
One line per question on what the interviewer is listening for, plus the likely follow-up.
Mistakes to avoid
The weak answer that costs points, so you can catch it in your own practice runs.
A PDF you can print
Read it on your phone before the call, or print the sections you want to drill.

Planned contents

The guide isn’t out yet, so chapters and their order may still change.

1. How the interview loop runs
2. How LLMs work
3. Prompting and context
4. Fine-tuning vs RAG
5. Cost and latency
6. A study plan for the weeks before

Free PDF

All 50 questions with model answers

A model answer for every question, what the interviewer is checking, the follow-up and the mistake to avoid.

Questions about the guide

Is the PDF really free?

Yes. Leave your email and we send the PDF the day it is ready. No payment details, and every email has a one-click unsubscribe link.

How is it different from the questions page?

The questions page lists every question with a handful of sample answers. The PDF has a model answer for each question, plus what the interviewer is checking, the likely follow-up and the mistake to avoid.

Is it based on a specific company’s interviews?

No. It is written from the concepts the role or system depends on. We don’t name companies or claim to know what any one company asks.

When will it be ready?

It isn’t out yet. Leave your email and we send it the day it is; nothing else arrives before then.