All courses
Free
intermediate

AI Engineering: From Zero to Working Models

Go from your first line of Python to building, testing, and explaining real machine learning and AI models. Every module uses free public data and asks the same hard question: should this model be built at all? Free, like every Community Incubator course.

Track
Engineering & Strategy
Length
20 weeks
Live sessions
Weekday evenings
Modules
19
Level
intermediate
Cost
Free

Outcome

Build, test, and explain machine learning and AI models on public data, and decide with evidence when a model should not be built.

Capstone

Build and present an end-to-end model on a public dataset for a real community question, with an ethics and judgment plan.

Focus areas covered

1 of 5 in the Engineering & Strategy track.

  • AI Engineering

Modules

  1. Module 1: What AI Engineers Actually DoSee the full path from a question to a working model, and learn the habit this course is built on: judgment before tools.2 lessons · 2 hours
  2. Module 2: Python Fundamentals 1: Data and DecisionsWrite Python that stores data, makes decisions, and repeats work. Everything runs in your browser.2 lessons · 3 hours
  3. Module 3: Python Fundamentals 2: Functions and StructurePackage your code into reusable functions and store records in dictionaries and JSON, the shape most real data arrives in.2 lessons · 3 hours
  4. Module 4: Data Preparation 1: Meet pandasLoad a real public dataset into a table, look at it, and clean the mess: wrong types, missing values, and duplicates.2 lessons · 3.5 hours
  5. Module 5: Data Preparation 2: Group, Join, ReshapeSummarize data by group, join two public tables on a shared key, and shape the result into one row per thing you want to predict.2 lessons · 3.5 hours
  6. Module 6: Sourcing Project Data: APIs and Scraping EthicsFind open data, request it from public APIs, keep keys safe, and decide when scraping a website is and is not acceptable.2 lessons · 3 hours
  7. Module 7: Data Visualization That Tells the TruthPick the right chart for the question, build charts in Python, and spot the tricks that make charts mislead.2 lessons · 3 hours
  8. Module 8: Predictions and Time SeriesWork with data that changes over time: find trends and seasons, build simple forecasts, and beat a baseline before you trust anything fancier.2 lessons · 3.5 hours
  9. Module 9: Unsupervised Learning: Finding GroupsFind structure in data that has no answer column: cluster similar rows, scale features fairly, and shrink many columns into a few.2 lessons · 3.5 hours
  10. Module 10: Regression: Predicting NumbersFit a line to data, use it to predict a number, and measure honestly how good the predictions are.2 lessons · 3.5 hours
  11. Module 11: Classification: Predicting CategoriesBuild models that sort things into categories, and learn why accuracy alone can hide the mistakes that matter most.2 lessons · 3.5 hours
  12. Module 12: Model Optimization: Better, Not Just BiggerSpot overfitting, tune models with cross-validation, and avoid the data leaks that make a model look better than it is.2 lessons · 3.5 hours
  13. Module 13: Data Ethics: Who Is Affected?Find bias before it ships, protect privacy (with extra care for minors), and decide with a clear test when a model should not be built.3 lessons · 4 hours
  14. Module 14: Neural Networks 1: How a Neuron LearnsBuild a single artificial neuron by hand, watch it learn from its mistakes, then stack neurons into layers.2 lessons · 3.5 hours
  15. Module 15: Neural Networks 2: Deep Learning in PracticeSee how networks train with gradient descent, train an image model on a public dataset, and know the costs and limits of deep learning.2 lessons · 4 hours
  16. Module 16: Natural Language ProcessingTurn text into numbers a model can use, build a text classifier on a public dataset, and see where language models fail people.2 lessons · 3.5 hours
  17. Module 17: Transformers and Large Language ModelsUnderstand attention, the idea behind modern language models, and learn to build with LLMs safely: prompts, API calls, testing, and limits.2 lessons · 4 hours
  18. Module 18: Emerging AI: Agents, RAG, and What Comes NextLearn how retrieval-augmented generation and AI agents work, and build a repeatable way to judge any new AI tool before you adopt it.2 lessons · 3 hours
  19. Module 19: Capstone: A Model That Earns TrustBuild one end-to-end project on public data for a real community question, with a judgment plan, and present it to a review board.2 lessons · 2 weeks