90-Day LLM Engineer Roadmap

Sprint from strong software engineer to production LLM engineer in 90 days.


Overview

WeekThemePrimary Output
1-2Vocabulary and mental modelsPersonal glossary, model card fluency
3-4How transformers and LLMs workArchitecture diagram, KV cache explanation
5-6Model cards, catalogs, selectionModel selection matrix for 5 use cases
7-8Local inference and hardwareBenchmark report for 3 local models
9-10Production servingvLLM deployment + throughput benchmark
11-12LLM gatewayWorking gateway with routing + cost tracking
13-14RAG systemsWorking RAG pipeline with eval
15-16Agents and tool callingWorking agent with observability
17-18EvaluationEval harness with model comparison
19-20Security, fine-tuningSecurity checklist + LoRA lab
21-22Startup playbookMVP spec + cost model
23-24CapstoneFull platform + demo narrative

Week 1 — LLM Vocabulary: Tokens, Context, Models

Goal: Be able to read any model card and understand every term.

Read:

Lab: Pick any two models from models.dev. List every term you do not understand. Look up each one in the vocabulary guide.

Artifact: Personal glossary with 40+ terms defined in your own words.


Week 2 — Vocabulary: Serving, Pricing, Local Models

Goal: Understand pricing, hardware, and serving terminology.

Read:

Lab: Read the OpenRouter pricing page. Understand every column and every term.

Artifact: Annotated pricing-page screenshot with every term explained.


Week 3 — Transformer Foundations: Big Picture to Attention

Goal: Explain tokenization → embeddings → attention → generation.

Read:

Lab: Run a tokenizer (tiktoken or HuggingFace tokenizer). Tokenize 10 different prompts. Observe token counts. Estimate costs.

Artifact: Tokenization study with 10 examples + cost calculations.


Week 4 — Transformer Foundations: KV Cache, Prefill, MoE

Goal: Understand why LLMs use memory and why batching matters.

Read:

Lab: Using the vLLM docs or any local model server, observe memory usage at different context lengths.

Artifact: Memory vs context length graph or table.


Week 5 — Model Cards and System Cards

Goal: Extract every relevant field from a model card in under 5 minutes.

Read:

Lab: labs/lab-00-model-card-reading/ — Read and annotate three model cards.

Artifact: Three completed model card worksheets.


Week 6 — Model Catalogs and Model Selection

Goal: Use models.dev fluently. Build a model selection matrix.

Read:

Lab: labs/lab-01-models-dev-explorer/

Artifact: Model selection matrix for 5 real use cases.


Week 7 — Local Inference: Hardware and GGUF

Goal: Run a local model. Understand hardware requirements.

Read:

Lab: labs/lab-02-local-llama-cpp/

Artifact: Hardware profile + llama.cpp benchmark report.


Week 8 — Local Inference: Quantization, Ollama, MTP

Goal: Compare quantization levels. Run Ollama. Understand MTP.

Read:

Labs: labs/lab-03-ollama-and-openai-compatible-api/ + labs/lab-05-quantization-benchmark/

Artifact: Quantization comparison benchmark.


Week 9 — Production Serving: vLLM Core

Goal: Deploy vLLM. Understand continuous batching, PagedAttention, streaming.

Read:

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

Artifact: vLLM benchmark: throughput vs batch size, latency vs context length.


Week 10 — Production Serving: Caching, Routing, Observability

Read:

Lab: Add prefix caching to vLLM setup. Observe hit rate and latency improvement.

Artifact: Cache hit rate study.


Week 11 — LLM Gateway: Architecture and Providers

Goal: Understand what an LLM gateway does and why.

Read:

Lab: labs/lab-07-model-gateway/ — Part 1: provider adapter and model registry.

Artifact: Working provider adapter with tests.


Week 12 — LLM Gateway: Routing, Metering, Streaming

Read:

Lab: labs/lab-07-model-gateway/ — Part 2: routing + streaming + cost tracking.

Artifact: Full gateway with routing config, cost dashboard, and streaming test.


Week 13 — RAG: Ingestion through Retrieval

Read:

Lab: labs/lab-08-rag-system/ — Part 1: ingestion, chunking, embedding, retrieval.


Week 14 — RAG: Reranking, Context Packing, Citations, Eval

Read:

Lab: labs/lab-08-rag-system/ — Part 2: reranking, citations, eval.

Artifact: RAG eval report with faithfulness and relevance scores.


Week 15 — Agents and Tool Calling

Read:

Lab: labs/lab-09-agent-with-tools/

Artifact: Working agent with 3+ tools, approval gates, and traces.


Week 16 — Agents: Memory, Browser, Code Execution

Read:


Week 17 — Evaluation Harness

Read:

Lab: labs/lab-11-eval-harness/

Artifact: Eval report comparing 3 models on your use case.


Week 18 — Observability and Production Operations

Read:

Lab: labs/lab-12-production-observability/


Week 19 — Security, Privacy, Governance

Read:

Artifact: Security checklist for your gateway project.


Week 20 — Fine-Tuning with LoRA

Read:

Lab: Fine-tune a small model with QLoRA. Evaluate before/after.


Week 21-22 — Startup Playbook

Read:

Artifact: MVP spec, cost model, and ICP statement for your startup idea.


Week 23-24 — Capstone

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

Deliver:

  • LLM gateway
  • RAG demo
  • Agent demo
  • Eval report
  • Architecture diagrams
  • Demo narrative

Quick Reference

If you want to...Go to...
Understand a term01-llm-vocabulary/
Read a model card03-model-cards-and-system-cards/
Choose a model05-model-selection/
Run a local model06-local-inference/
Deploy vLLM07-production-serving/01-vllm.md
Build a gateway08-llm-gateways/
Build RAG09-rag/
Build an agent10-agents-and-tools/
Run evals12-evaluation/
Start a company15-startup-playbook/