Getting Started

A welcome letter, your environment, and a live portfolio site. Free for everyone — no account required.

Ship an End-to-End ML Product

Eleven modules that take you from maintainable Python to a deployed, monitored ML product you build yourself.

Module 1

Python for ML Engineers

Move from writing Python scripts to building maintainable ML software: importable packages, typed data contracts, and reproducible environments.

8 lessons
Module 2 · Coming soon

Data Wrangling & ML Pipelines

Turn messy data into reliable features: one deterministic transform that produces identical output at train time and at serve time.

7 lessons
Module 3 · Coming soon

Numerical & Statistical Foundations

Understand when a model result is trustworthy: imbalance, leakage, the metrics that lie, and splits that estimate the future.

7 lessons
Module 4 · Coming soon

Classical Machine Learning

Train models that solve real problems — and know when a better leaderboard number is a worse product: trees, XGBoost, calibration, serialization.

7 lessons
Module 5 · Coming soon

Packaging & Reproducibility

Make the ML system run anywhere: the same model, the same dependencies, the same result, on a machine that has never seen the code.

8 lessons
Module 6 · Coming soon

APIs & Model Serving

Turn a model into a service other code can call: schema-validated, batch-capable, honest about its latency, and a stable contract for its consumers.

7 lessons
Module 7 · Coming soon

Frontend & ML Product Thinking

Put the model in a non-ML human's hands: a minimal dashboard that calls the API and shows a prediction someone can act on — without lying about confidence.

5 lessons
Module 8 · Coming soon

Cloud Deployment

Make the system publicly usable: a stranger can reach it at a real URL, over TLS, with one-step rollback and a bounded, stated cost.

7 lessons
Module 9 · Coming soon

Infrastructure as Code

Make the infrastructure reproducible the way Docker made the app reproducible: declarative, versioned, reviewable infra — the principle, not Terraform syntax.

6 lessons
Module 10 · Coming soon

Monitoring, Observability & Reliability

Know when your system is failing — including the case where it returns 200 OK and is quietly wrong: metrics, drift, alerting, and silent failures.

7 lessons
Module 11 · Coming soon

MLOps: CI/CD & Retraining

Build systems that improve safely: CI that tests data and models, and a retraining loop that rolls out a new model version without betting the whole system on it.

7 lessons