Paths · 12 modules · 69 lessons · 5 projects · about 21 hours
ML Engineer
Train models and ship them: data, classical ML, neural networks, training, evaluation and serving.
Who it's for
Developers or analysts comfortable with Python who want to train and deploy models.
By the end, you can
- Prepare data and train classical and neural models that generalise
- Implement core algorithms from scratch and debug training
- Serve models fast and cheaply, and monitor them in production
Not startedStart the path →
The route
Modules in order, with a project after the lessons it builds on. Mark lessons as done and tick project steps, and this page tracks your progress. Sign in to keep it on every device.
- Module 01 · 5 lessons · about 19 minPython and maths toolkitVectors, probability and gradients, with NumPy.Not started
- Module 02 · 8 lessons · about 30 minClassical machine learningRegression, trees, boosting, and how to tell if a model is any good.Not started
- Project · Beginner · 3–4 hours · ProBuild a spam filterTrain logistic regression from scratch on real text messages, then decide how strict the filter should be.5 steps
- Module 03 · 7 lessons · about 25 minNeural networksFrom one neuron to backprop, by hand, with small numbers.Not started
- Project · Intermediate · 3–5 hours · ProA neural network in NumPyWrite the forward pass, backpropagation and training loop yourself, and prove your gradients are right.5 steps
- Module 04 · 3 lessons · about 11 minDeep learning in PyTorchTensors, autograd and training loops: the tools real ML work uses.Not started
- Project · Intermediate · 3–4 hours · ProRecognise handwriting with PyTorchTrain a small convolutional network that reads handwritten digits, and learn the PyTorch workflow every ML team uses.5 steps
- Module 05 · 4 lessons · about 18 minTokens and embeddingsHow text becomes numbers a model can work with.Not started
- Module 06 · 6 lessons · about 26 minTransformersAttention, the full architecture, and how the next token is chosen.Not started
- Module 07 · 8 lessons · about 29 minTraining and fine-tuningPretraining, LoRA, preference tuning and the data behind them.Not started
- Project · Advanced · 3–4 hours · ProFine-tune a language model with LoRATeach a real language model a new style by training less than 0.2% of its weights, on a laptop CPU.5 steps
- Module 11 · 5 lessons · about 16 minEvaluationDecide what good means, then measure it without fooling yourself.Not started
- Module 12 · 6 lessons · about 19 minInference and servingWhere the time goes, and how to make models fast and cheap.Not started
- Module 13 · 7 lessons · about 21 minProduction AI and MLOpsRouting, fallbacks, budgets, monitoring and safety in real systems.Not started
- Project · Intermediate · 2–3 hours · ProPut your project onlineTurn the notes search engine into a tested web API, package it with Docker, and give it a public address.6 steps
- Module 14 · 5 lessons · about 16 minML system designA repeatable way to design recommenders, search and LLM products.Not started
- Module 16 · 5 lessons · about 19 minML from scratchWrite k-means, attention and a tokenizer from scratch.Not started