AI/ML Engineering

Introductory chapter: AI's capabilities and limitations, impact on architecture and careers.

A broad historical and engineering panorama of AI: from ancient computing ideas and the perceptron to AlexNet, deep learning, and foundation models, with focus on how algorithms, infrastructure, and product practices evolved together.

An introductory guide to AI algorithms: search, evolutionary methods, swarm intelligence, ML, ANN, and Q-learning. Best read together with modern LLM/GenAI sources.

A concise intro to deep learning and data science: fundamentals, classical ML algorithms, hands-on tasks, and practical walkthroughs with TensorFlow, Keras, and PyTorch.

Chip Huyen on creating AI applications: foundation models, prompting, RAG, agents, finetuning, quality assessment and production practices.

Jay Alammar and Maarten Grootendorst: visual guide to LLM with ~300 illustrations - tokenization, embeddings, transformers, RAG.

Jay Alammar and Maarten Grootendorst: a practical guide to AI agents - memory, tools, planning, reflection, multi-agent coordination, and engineering risks.

John Berryman and Albert Ziegler (creators of GitHub Copilot): LLM Loop, RAG, agents, workflows and the transition to context engineering.

Original chapter about production GenAI/RAG architecture: ingestion, retrieval, orchestration, guardrails, evaluation, and latency/cost trade-offs.

A concise practical 2023 guide to getting started with LLM apps: OpenAI API basics, prompting, prompt injection mitigation, lightweight fine-tuning, and early LangChain patterns.

A simple and practical explanation of precision/recall, their trade-off and threshold selection using the example of “Vasya and the Wolf”.

How Google went from TPU v1 for inference to Ironwood: architectural decisions, economics of AI infrastructure and comparison with the GPU approach.

Analysis of the history of Lovable, business model and conceptual architecture of the vibe-coding platform: from open-source CLI to cloud product with agent workflow.

Analysis of the Dyad architecture: multi-process Electron, agent+tool orchestration, template-driven development and local-first approach with a checkpoint model.

Analysis of an interview about the development of the ML platform at T-Bank: from SSH circuits to platform engineering, data workflows and production operation.

Extended report on the transition from AI assistants to agent scenarios in the SDLC: tools, protocols, governance, performance assessment and practical implementation cases.

The official PyTorch documentary about how the framework grew from an experiment to the foundation of an AI ecosystem.

Documentary about AlphaGo's match against Lee Sedol and the breakthrough in artificial intelligence.

Documentary about DeepMind, AGI and Demis Hassabis: the path from AlphaGo to the Nobel Prize for AlphaFold.

Speech by Yandex CTO Alexey Gusakov on the transition from coding algorithms to designing intentions, restrictions, metrics and reward cycles in LLM products.