Curriculum
19 tracks and 2 collections. Learning order is guidance, not a gate.
What AI engineering is, and how it differs from ML and research.
The engineering base: APIs, streaming, queues, testing, deployment.
Vectors, probability, training, metrics, and the statistics interviews probe.
Attention, tokenization, inference mechanics, and the transformer block.
Tokens, decoding, structured output, tool calls, and cost.
Instructions, context assembly, and defending untrusted input.
From parsing and chunking to hybrid retrieval, reranking and citations.
Loops, tools, memory, approvals, durable execution, and when not to use an agent.
Repository context, patch editing, verification, worktrees and sandboxing.
MCP, A2A, and the difference between capability access and delegation.
SFT, LoRA, preference optimisation, and when tuning is the wrong tool.
Vision, speech, real-time voice, and document understanding.
Golden sets, judges, regression gates, and error analysis.
Injection, exfiltration, excessive agency, and layered controls.
Latency, cost, observability, failover, and incident response.
Reference architectures and twelve end-to-end design walkthroughs.
SQL, modelling, pipelines, and vector stores next to relational data.
Answer frameworks, drills, take-homes, and behavioural preparation.
LangGraph, LangChain, LlamaIndex, CrewAI, SDKs, and how to choose.
Infrastructure comparisons: providers, vector stores, serving, observability.
Reusable topologies: queues, fan-out, cache-aside, sidecars, event-driven evals.