Home › Paths › LLM Engineering › AWS

Learning path · AWS

LLM Engineering on AWS

You work on the models themselves: data, tuning, serving and cost per token.

Free, like everything here: no sign-up, no paywall. Only the cloud you practise on may charge; the open-source path costs nothing.

AI engineers use models; LLM engineers shape them. That means knowing how a model is trained, how to adapt one to a task, how to serve it fast and cheap, and when a small model beats a big one.

Every topic below is a concept (the job) with the AWS product that does it. Learn the concept once; on another platform only the product name changes. Read alongside: The AI Universe · Agent Harness, drawn simply · Certification prep on this site.

Beginner · 6 weeks

Crawl: You can build one thing end to end, with help.

Understand how a language model works by building a tiny one, then use real ones well.

Key ideas at this level, the same on every platform:

Learn

LearnWhat it meansOn AWS you use
How a model workstokens, embeddings, attention, next-token predictionPythona language, properly
Tiny model by handtrain a very small model on your laptopSageMaker training jobstraining
Using hosted modelsprompts, context windows, cost and speedAmazon Bedrockmodel api
Bedrock Converse APIprompts and structured output
Embeddingsturn text into vectors; search by meaningOpenSearch Serverless / Aurora pgvectorvector search

Build on GitHub

Under way · join

LearnLLMStack

A tiny version of every layer of an LLM product, from your own small model up to the app, in one stack.

Built on Open source today. Porting it to AWS is a good first contribution.

Proposed · needs a lead

Ask your documents, with citations

Search a folder of PDFs and answer with the exact passage cited, plus a 50-question test set you run on every change.

You are ready to move on when

Intermediate · 3 months

Walk: You can build it so it keeps working, without help.

Adapt and serve models: fine-tune, host open weights and measure quality and cost.

Key ideas at this level, the same on every platform:

Learn

LearnWhat it meansOn AWS you use
Fine-tuningwhen to tune and when to prompt; LoRA; good examplesBedrock custom models / SageMakerfine-tuning
Serving open modelsbatching, quantisation, throughputSageMaker endpoints / EKS + vLLMmodel hosting on gpus
Evaluationtask metrics, judge models, human reviewBedrock evaluationsevaluation
Cost per tokenmeasure it, then cut it with caching and routingBedrock cross-region inference + API Gatewaymodel gateway
Cost Explorer + CURcost

Build on GitHub

Proposed · needs a lead

Fine-tune a small model

Teach a small open model one narrow task from a big model's examples, then compare quality, speed and cost honestly.

Under way · join

LLM cost explainer

Turn a provider's usage export into a plain report: where the money went and what to change.

Built on Open source today. Porting it to AWS is a good first contribution.

Just starting · join

MyClaudeCode

A small coding agent built from scratch, to learn how context is budgeted and how tools are kept safe.

Built on Open source today. Porting it to AWS is a good first contribution.

You are ready to move on when

Advanced · 6 months +

Run: You can design it, prove it and lead others through it.

Build the data and training pipeline for a model, and publish it.

Key ideas at this level, the same on every platform:

Learn

LearnWhat it meansOn AWS you use
Training data at scalecollect, clean, dedupe, filter, licenseEMR / Glue on S3training data at scale
Amazon S3object storage
Pre-training and post-trainingcontinued pre-training, instruction tuning, preference tuningBedrock custom models / SageMakerfine-tuning
SageMaker endpoints / EKS + vLLMmodel hosting on gpus
Benchmarkshonest evaluation in a new language or domainBedrock evaluationsevaluation
Safetyred-teaming and guardrails for your modelBedrock Guardrailsguardrails

Build on GitHub

Needs a lead

Hinglish pre-training data

Build a clean, licensed, de-duplicated Hinglish text corpus and a small model trained on it.

Needs a lead

Robotics data benchmark

A benchmark for the data pipelines that feed robot learning: formats, quality and cost.

You are ready to move on when

Optional

Certifications on AWS

Projects prove more than certificates, but a certificate can open a door. These fit this path. Exam names and codes change, so check the current one before you book.

Free prep we have written: Certifications.

Learn together

Do it with others

Every project above has a page, a list of open work and a "good first issue" label on GitHub. Pick one at your level, say hello by email, and build it in the open. If a project says needs a lead, that can be you.

All projects →   Another path →