Home › Paths › LLM Engineering › Databricks
Learning path · Databricks
LLM Engineering on Databricks
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 Databricks 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
| Learn | What it means | On Databricks you use |
|---|---|---|
| How a model works | tokens, embeddings, attention, next-token prediction | Pythona language, properly |
| Tiny model by hand | train a very small model on your laptop | Databricks ML runtimetraining |
| Using hosted models | prompts, context windows, cost and speed | Foundation Model APIsmodel api ai_query + structured outputprompts and structured output |
| Embeddings | turn text into vectors; search by meaning | Vector Searchvector search |
Build on GitHub
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 Databricks is a good first contribution.
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
- You can explain attention to a friend with a drawing.
- Your search finds the right passage for 8 of 10 test questions.
- You know the cost per 1,000 answers.
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
| Learn | What it means | On Databricks you use |
|---|---|---|
| Fine-tuning | when to tune and when to prompt; LoRA; good examples | Mosaic AI fine-tuningfine-tuning |
| Serving open models | batching, quantisation, throughput | Provisioned throughput servingmodel hosting on gpus |
| Evaluation | task metrics, judge models, human review | MLflow evaluationevaluation |
| Cost per token | measure it, then cut it with caching and routing | Mosaic AI Gatewaymodel gateway Billing system tablescost |
Build on GitHub
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.
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 Databricks is a good first contribution.
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 Databricks is a good first contribution.
You are ready to move on when
- Your small tuned model matches the big one on your task at a fraction of the cost.
- You can serve it and state the tokens per second.
- Your evaluation would catch a worse model.
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
| Learn | What it means | On Databricks you use |
|---|---|---|
| Training data at scale | collect, clean, dedupe, filter, license | Spark on Deltatraining data at scale Unity Catalog volumes on cloud storageobject storage |
| Pre-training and post-training | continued pre-training, instruction tuning, preference tuning | Mosaic AI fine-tuningfine-tuning Provisioned throughput servingmodel hosting on gpus |
| Benchmarks | honest evaluation in a new language or domain | MLflow evaluationevaluation |
| Safety | red-teaming and guardrails for your model | AI Gateway guardrailsguardrails |
Build on GitHub
Hinglish pre-training data
Build a clean, licensed, de-duplicated Hinglish text corpus and a small model trained on it.
Robotics data benchmark
A benchmark for the data pipelines that feed robot learning: formats, quality and cost.
You are ready to move on when
- Your dataset has a data card, a licence and a de-duplication report.
- You have trained and evaluated a model on it.
- Others can reproduce your result.
Optional
Certifications on Databricks
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.
- Databricks Generative AI Engineer Associate
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.