Start Here — LLM Inside-Out Mastery

Read this before anything else.


What You Are Building Toward

You are building the mental model and hands-on skills of a seasoned LLM engineer.

That means you can:

  1. Talk to the model — Understand tokens, context, sampling, generation
  2. Choose the right model — Read model cards, use catalogs, compare providers
  3. Run models anywhere — Local, cloud, self-hosted, API, gateway
  4. Build with models — RAG, agents, tools, structured output, streaming
  5. Serve models — vLLM, continuous batching, PagedAttention, KV cache
  6. Route and meter — LLM gateway, fallbacks, cost tracking
  7. Evaluate rigorously — Correctness, latency, cost, safety, regression
  8. Operate safely — Security, privacy, prompt injection, governance
  9. Build products — Startup playbook, unit economics, MVP

The Right Mental Model From Day 1

An LLM is a token probability machine.

It takes a sequence of tokens as input and predicts the probability distribution over the next token. It does this one token at a time. Everything else — tool calling, structured output, agents, RAG, reasoning — is application logic wrapped around this core.

You control quality through context.

The model only knows what is in its context window. Everything the model "knows" beyond that came from training. Your job as an LLM engineer is to ensure the right context is in the window at the right time.

Cost is tokens times price.

Every call costs (input tokens × input price) + (output tokens × output price). Model routing, caching, context compression, and chunked retrieval are cost controls.

Latency has two phases.

TTFT (time to first token) depends on prefill speed. TPOT (time per output token) depends on decode speed. Streaming makes products feel faster. Batching increases throughput at the cost of individual TTFT.

Safety is your application's responsibility.

The model's safety training helps but cannot be relied on. You must add output validation, prompt shields, tool approval, rate limits, and audit logs.


Recommended Entry Path

Week 1-2: Vocabulary and Mental Models

Start with Phase 1 (vocabulary) and Phase 0 (orientation).

Goal: be able to read a model card and understand every term.

01-llm-vocabulary/00-core-mental-model.md01-llm-vocabulary/09-complete-glossary.md00-orientation/00-what-is-an-llm-engineer.md

Lab: Read three model cards from scratch. Extract every field using the model card checklist.


Week 3-4: How LLMs Work

Phase 2 (transformer foundations).

Goal: explain tokens → embeddings → attention → generation → KV cache to a non-engineer.

02-transformer-foundations/00-transformer-big-picture.md02-transformer-foundations/06-kv-cache.md02-transformer-foundations/07-prefill-vs-decode.md

Lab: Run a small model locally and observe tokens/sec, TTFT, and memory usage.


Week 5-6: Model Cards, Catalogs, and Model Selection

Phases 3 and 4.

Goal: build a model selection matrix for five real use cases.

03-model-cards-and-system-cards/00-how-to-read-model-cards.md04-model-catalogs-and-trend-reading/00-how-to-use-models-dev.md05-model-selection/00-model-selection-framework.md

Lab: Build a model selection memo for a coding agent, a RAG assistant, and a document summarizer.


Week 7-8: Local Inference

Phase 6.

Goal: run three different models locally, benchmark them, compare quantization.

06-local-inference/00-local-inference-overview.md06-local-inference/03-gguf-and-llama-cpp.md06-local-inference/06-quantization-guide.md

Labs: labs/lab-02-local-llama-cpp/ and labs/lab-05-quantization-benchmark/


Week 9-10: Production Serving

Phase 7.

Goal: run vLLM, benchmark throughput, understand PagedAttention and continuous batching.

07-production-serving/00-serving-architecture.md07-production-serving/01-vllm.md

Lab: labs/lab-04-vllm-serving/


Week 11-12: LLM Gateway

Phase 8 + Lab 7.

Goal: build a functional LLM gateway with routing, fallback, cost tracking, and streaming.

08-llm-gateways/00-what-is-an-llm-gateway.md

Lab: labs/lab-07-model-gateway/


Month 2: RAG + Agents + Eval

→ Phases 9, 10, 12

Labs: labs/lab-08-rag-system/ and labs/lab-09-agent-with-tools/


Month 3: Fine-tuning, Security, Startup

→ Phases 13, 14, 15

Lab: labs/lab-13-capstone-platform/


What to Produce As You Go

PhaseArtifact
VocabularyPersonal glossary with notes
Transformer foundationsArchitecture diagram with annotations
Model cardsModel card reading checklist + 3 sample memos
Model selectionModel selection matrix for 5 use cases
Local inferenceBenchmark report for 3 models
Production servingvLLM deployment and benchmark report
LLM gatewayWorking gateway with routing config
RAGWorking RAG system with eval results
AgentsWorking agent with tool calls and traces
EvalEval harness with model comparison report
StartupMVP spec, cost model, and demo narrative

What This Is Not

  • Not a machine learning research curriculum.
  • Not a deep learning from scratch course.
  • Not a data science course.
  • Not a Python tutorial.

You do not need to implement backpropagation. You do not need to train models from scratch. You need to understand how to engineer, serve, evaluate, and build on top of LLMs.


How to Study Fast-Moving AI

  1. Primary sources first. Model cards, official docs, arxiv abstracts, changelogs.
  2. Ignore hot takes. Most "new technique" posts describe ideas that are not yet production-ready.
  3. Benchmark everything yourself. External benchmarks are environment-specific.
  4. Build fast, evaluate quickly. A working lab beats a finished reading list.
  5. Track the spec, not the demo. Demos are curated. Read the methodology.
  6. Watch release notes, not announcements. Announced capabilities vs shipped capabilities differ.

How to Use the External References

Every document in this curriculum lists external references with:

  • Title and URL
  • Why it matters
  • What sections to read first
  • How it connects to the lab

Do not try to read every reference. Use them as on-demand lookups when you hit a concept you need to understand more deeply.


→ Ready? Start with 01-llm-vocabulary/00-core-mental-model.md