Skip to content
LeetLLM
Tracks
Beginner23 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 AIBuild a reproducible AI repo with safe Git defaults, a clean-clone eval gate, shell diagnostics, and Linux process habits.Computing FoundationsEasy20 min
  2. 2Docker for Reproducible AIPackage the access-request scorer in a portable Docker image with a small build context, mounted data, runtime configuration, a non-root user, and a reproducible gate.Computing FoundationsEasy18 min
  3. 3Python for AI EngineeringLearn Python by building a small evaluator: read JSONL, validate fields, count correct predictions, and test the difference between bad input and a wrong answer.Computing FoundationsEasy17 min
  4. 4NumPy 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 FoundationsEasy20 min
  5. 5Data Structures for AIChoose Python lists, hash-based collections, deques, heaps, trees, graphs, tries, and caches by the operations an AI system must serve.Computing FoundationsEasy21 min
  6. 6SQL and Data ModelingTurn an in-memory support retriever into durable SQL tables. Model versioned sources, query safely, preserve permissions and lineage, and inspect the paths that keep retrieval correct as data changes.Computing FoundationsEasy24 min
  7. 7Dataset Pipelines and Data QualityBuild versioned AI datasets with schema gates, grouped splits, contamination checks, and auditable receipts.ML Algorithms & EvaluationMedium29 min
  8. 8Gradients and BackpropTrain a one-weight latency predictor by reading a slope, taking a downhill step, tracing chain-rule paths, and checking the same gradient in PyTorch.Math & StatisticsEasy22 min
  9. 9Vectors, Matrices & TensorsTrace one latency prediction into matrix products and token tensors. Check shapes, distinguish dot products from cosine similarity, and catch silent axis mistakes.Math & StatisticsEasy18 min
  10. 10Probability for Machine LearningUse one API abuse-risk detector to learn events, random variables, distributions, conditional probability, independence, Bayes rule, and base-rate mistakes.Math & StatisticsEasy21 min
  11. 11Statistics and UncertaintyEstimate a review queue's abuse rate with bootstrap and Wilson intervals, distinguish sampling variation from bias, and assess calibration without overstating the evidence.Math & StatisticsEasy20 min
  12. 12Neural Networks from ScratchBuild a CodeAssist timeout-risk neural network from scratch: derive affine maps, prove why non-linearities prevent layer collapse, compare core activations, track batched tensor shapes, and implement backpropagation with NumPy and PyTorch autograd.Preparation & PrerequisitesEasy23 min
  13. 13Training & BackpropagationFollow a decode-latency model through reverse-mode autograd, the PyTorch training loop, batching dynamics, vanishing gradients, weight initialization, and early stopping.Preparation & PrerequisitesEasy27 min
  14. 14PyTorch Training LoopsTrace logits, gradients, updates, and validation in runnable PyTorch loops. Work through unequal micro-batches, CUDA AMP ordering, independent snapshots, and checkpoint resumption.ML Algorithms & EvaluationMedium34 min
  15. 15The Transformer Architecture End-to-EndTrace a three-token prompt through causal attention, residual updates, and a vocabulary head. Build and test one complete decoder in PyTorch.Preparation & PrerequisitesEasy25 min
  16. 16Language 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 & PrerequisitesEasy28 min
  17. 17From GPT to Modern LLMsTrace how decoder-only models grew into modern LLMs, then inspect scaling, instruction tuning, open weights, MoE, and serving tradeoffs with runnable examples.Preparation & PrerequisitesEasy31 min
  18. 18BPE, WordPiece, and SentencePieceBuild a subword tokenizer, master BPE, WordPiece, and SentencePiece Unigram, and debug production failure modes from fertility tax to glitch tokens.Core LLM FoundationsMedium31 min
  19. 19Static 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 FoundationsMedium25 min
  20. 20Prompt Engineering FundamentalsBuild an incident-triage prompt with clear roles, useful examples, structured outputs, evidence checks, and a separate authorization boundary.Preparation & PrerequisitesEasy14 min
  21. 21Calling LLM APIs in ProductionTurn a grounded prompt into a reliable API boundary with server-side secrets, typed results, bounded retries, safe actions, and useful telemetry.Preparation & PrerequisitesEasy28 min
  22. 22First AI App End-to-EndRun one local rotation-decision app with a browser form, checked provider boundary, durable traces, and tests of the actual HTTP path.Preparation & PrerequisitesEasy13 min
  23. 23LLM Benchmarks & LimitationsBuild an evaluation suite for a policy-answering LLM: score evidence use, understand public benchmark contracts, control judge bias, and make release decisions from private tests.Core LLM FoundationsMedium33 min