Course

ML interview course: interactive lessons

121 short interactive lessons (about 34 hours in all) that teach the ideas ML interviews test, from classical models and deep learning to LLMs, reinforcement learning and ML system design. Each lesson lists what you will learn and what to take first.

Start here

The job and the interviews

Chapter 1: Classical ML

Your first model, end to end

Making it work on new data

Beyond straight lines

Can you trust the output?

No labels, and time

Chapter 2: Deep learning

Neural networks and backpropagation

Optimizers, normalization and training stability

Why big networks generalize

CNNs and computer vision

Sequence models and contrastive embeddings

Learning on graphs

Generative models: VAEs, diffusion and GANs

Chapter 3: LLM foundations

Tokens and embeddings

Attention and the transformer

Modern LLM architectures

Pretraining at scale

Chapter 4: LLM inference

Decoding and sampling

The inference cost model

Serving optimizations

Quantization

Chapter 5: Reinforcement learning and post-training

Reinforcement learning basics

Fine-tuning: SFT and PEFT

Preference alignment

RL for reasoning

Chapter 6: LLM applications

Prompting and guardrails

Retrieval and search

RAG pipelines

Evaluating LLM systems

Agents

Chapter 7: ML system design and experiments

The design framework

Fraud and risk systems

Search and ads

Recommendation systems

GenAI system design

A/B testing