17 free courses, no signup wall
Architect-led enterprise cloud, security & AI
Fixed-price engagements, scoped on a discovery call
Skip to content
Engineer

AI Engineer

Build the retrieval, prompting, and evaluation machinery that turns a model into a product.

Who this is for

Engineers shipping LLM and RAG features that other people depend on.

What you should be able to do

Ship a retrieval pipeline with evaluation, structured outputs, and a rollback path.

Career ladder

The titles this track maps onto. Levels differ between companies. The useful part is the direction, and what each step adds to the one before it.

  1. AI Developer
  2. AI Engineer
  3. Senior AI Engineer
  4. Principal AI Engineer
  5. Distinguished Engineer

Tech stack

What the work is actually done with. Grouped by the job each tool does, so the list reads as a system rather than a pile of names.

Language
PythonTypeScript
Serving
FastAPIRay Serve
Orchestration
LangChainLangGraphMCP
Models
ClaudeGPTGeminiBedrockAzure OpenAIOllama
Retrieval
pgvectorPineconeWeaviateQdrant

The delivery flow

The order the work actually happens in. Each step is where a decision gets made and written down, not a chapter heading.

  1. Requirement
  2. Data ingestion
  3. Chunking + embedding
  4. Vector store
  5. Retrieval + rerank
  6. Prompt + structured output
  7. Evaluation harness
  8. Deploy + observe

Reference repository structure

A starting layout for this track. The directories are the ones that get added late and hurt. Decisions, evals, policy, lineage. Promoted to the top level where they are visible.

ai-service/
├── app/
│   ├── api/               # FastAPI routers, request/response models
│   ├── chains/            # retrieval + generation composition
│   ├── prompts/           # versioned, one file per prompt
│   └── schemas/           # structured output contracts
├── ingestion/
│   ├── loaders/           # source connectors
│   ├── chunking/          # strategy per document type
│   └── embed.py
├── evals/                 # golden set, metrics, regression gate
├── infra/                 # terraform, docker, k8s manifests
└── tests/

Reading path

12 published guides on this track. Every one is a live page on this site. Nothing here is a placeholder.

  1. Building Production RAG Pipelines with LangChain & Claude
  2. How to Build a Production RAG Pipeline on AWS Bedrock in 2026
  3. RAG vs Fine-Tuning: Which Should Enterprises Use? [2026]
  4. Vector Databases for RAG: pgvector, Pinecone, Weaviate & Milvus
  5. AI Engineering Course: LLMs, RAG, Agents [2026]
  6. Building Production RAG Pipelines: A Senior Engineer's Guide
  7. Building Production RAG Pipelines: Engineer's Guide
  8. How to Build a DevSecOps Pipeline from Scratch [2026 Guide]
  9. How to Build a DevSecOps Pipeline from Scratch: A Step-by-Step Guide for 2026
  10. RAG Pipeline in Production: From Prototype to Enterprise-Grade in 2026
  11. LangChain vs LlamaIndex vs AutoGen: Which AI Framework for Enterprise in 2026
  12. LangChain vs LlamaIndex vs AutoGen: Which AI Framework? [2026]

Reference implementations

Citadel’s open-source repositories for this track. Terraform modules, MCP servers, and reference architectures you can read, fork, and run. Apache/MIT licensed; check each repository for its terms.

Primary sources

The standards, framework documents, and vendor references this track is built against. Go here when you need the authoritative wording rather than a summary. In a security review or an audit, the source is what counts.

Other tracks

Talk through this with an architect