LeetLLM
Tracks
Beginner12 lessons

AI Engineer Foundations

Start from software and math basics, then build toward first LLM applications without guessing the prerequisite order.

Software engineers, students, and career switchers new to ML systems.

You can read model diagrams, run Python experiments, call LLM APIs, and explain the first full AI app path.

  1. 1Git, Shell, Linux for AIMaster the local engineering environment production AI systems depend on: version control for code/data/models, shell one-liners for GPUs and datasets, Linux fundamentals, and reproducible setups that survive laptop changes and team handoff.Computing FoundationsEasy10 min
  2. 2Python for AI EngineeringLearn Python as the first AI engineering loop: read JSONL rows, validate fields, compute exact-match accuracy, and harden the scorer with pytest, prompt snapshots, leakage checks, seeded runs, and a CI gate.Computing FoundationsEasy15 min
  3. 3NumPy and Tensor ShapesLearn NumPy shape reasoning from first principles: name axes, predict indexing and broadcasting, reduce safely, distinguish reshape from transpose, and add shape guards.Computing FoundationsEasy17 min
  4. 4Vectors, Matrices & TensorsTurn one gradient vector into batches of model inputs while learning dot products, matrix transforms, tensor axes, and shape debugging.Math & StatisticsEasy12 min
  5. 5Probability for Machine LearningA beginner-first probability article that teaches events, priors, conditional probability, independence, Bayes rule, and base-rate mistakes through one API abuse-risk detector story.Math & StatisticsEasy19 min
  6. 6Neural Networks from ScratchTrace a incident-risk network from one neuron to a batched NumPy forward pass, then diagnose activation, shape, scale, and numerical-stability failures.Preparation & PrerequisitesEasy11 min
  7. 7The Transformer Architecture End-to-EndTrace a support reply through masked attention, a decoder block, and next-token logits with readable NumPy and PyTorch code.Preparation & PrerequisitesEasy13 min
  8. 8Language Modeling & Next TokensLearn how next-token prediction becomes a trainable language model, from bigram counts and neural n-grams to causal Transformer generation and KV-cache serving.Preparation & PrerequisitesEasy24 min
  9. 9BPE, WordPiece, and SentencePieceBuild a small subword tokenizer, compare BPE, WordPiece, and SentencePiece, then audit token cost and Unicode behavior.Core LLM FoundationsMedium20 min
  10. 10Static to Contextual EmbeddingsTurn token IDs into vectors, learn what nearby usage captures, and see why a word such as charge needs sentence-dependent representations.Core LLM FoundationsMedium15 min
  11. 11Prompt Engineering FundamentalsBuild and test grounded prompts with clear roles, few-shot examples, structured outputs, evidence checks, and failure-focused evaluation.Preparation & PrerequisitesEasy18 min
  12. 12First AI App End-to-EndShip one traceable rotation-decision workflow: validated input, model boundary, stored status, clear UI states, failure tests, and deploy checks.Preparation & PrerequisitesEasy13 min