README.md

AI & ML

Updated 2 min read index source

AI & ML

Foundations through advanced, for a Python backend engineer moving into AI/ML work. Rebuild complete (phases 3.1-3.6). 44 files at the start of this effort, 124 now.

Baseline facts and current versions: Stack baseline — 2026-2027.

Built

# Folder Covers
00 Math foundations linear algebra, probability/stats, calculus & optimisation, information theory
01 ML foundations problem types, splits, bias-variance, regularisation, lifecycle, when not to use ML
02 Classical ML linear/logistic, trees, random forest, gradient boosting, SVM, kNN/NB, clustering, PCA
03 Feature engineering encoding, scaling, selection, data leakage, imbalanced data, feature stores
04 Model evaluation confusion matrix, precision/recall, ROC-AUC vs PR-AUC, regression metrics, calibration
05 Deep learning networks, activations, training, CNN, RNN/LSTM, norms & residuals, transfer learning
06 Transformers and LLMs architecture, GQA/MLA, tokenization, RoPE, KV cache, MoE, reasoning models, context
07 Training and fine-tuning pretraining, SFT, DPO/GRPO/RLVR, quantization, fine-tune vs RAG
08 Inference and serving prefill vs decode, continuous batching, PagedAttention, speculative decoding
09 RAG and embeddings RAG, embeddings, chunking, hybrid search + reranking, agentic RAG, retrieval eval
10 Agents and orchestration agent loop, LangGraph 1.0 durable execution, multi-agent, A2A, failure modes
11 Model Context Protocol fundamentals, the 2026-07-28 stateless-core revision, building and securing servers
12 Context engineering context budgeting, ordering, compaction, memory systems
13 Evaluation why eval is hard, building eval sets, LLM-as-judge biases, online experiments
14 Guardrails and safety prompt injection, output validation, PII, EU AI Act 2026
15 MLOps and LLMOps MLflow, registry, drift, OTel GenAI observability
16 ML frameworks PyTorch, TensorFlow, scikit-learn, JAX, Optuna — the 2026 map
17 ML system design the design framework, RAG assistant, fraud detection
18 Speech and realtime AI STT/TTS, streaming vs batch, realtime voice agents, turn detection and barge-in

Reading order

For a backend engineer preparing for an AI-facing role: 01_ml_foundations first (it’s the judgement layer and the most transferable), then 02_classical_ml for the tabular questions, then the LLM stack. 00_math_foundations is reference — dip into it when a specific question needs it rather than reading it front to back.

Contents 172