Skip to main content

Interactive roadmap

AI Engineer

From programming foundations to production AI systems

A step-by-step skill map for engineers building practical products with foundation models, RAG, agents, evaluation, and production infrastructure.

6–12 monthsBackend and Python developersSoftware engineersTechnical product buildersAI practitioners
Open as course →Every node has an evidence route
6stages
33nodes
5projects and milestones
01 · Engineering foundations02 · LLM engineering core03 · RAG and knowledge systems04 · Agents and tool ecosystems05 · Evaluation, safety, and quality06 · Production AI systems and runtime operations
  1. 01

    Engineering foundations

    The base required to keep AI products from turning into fragile demos.

    Stage outcomeA reliable Python/API project with typing, tests, and controlled error handling.
    3–5 weeksMaterials ready
    Topic →
    Materials ready
    Prerequisites: Production Python
    Article →
    Materials readyAssessment available
    Prerequisites: Production Python, HTTP, APIs, and backend fundamentals
    Open practicum →Assessment rubric →Practicum →
  2. 02

    LLM engineering core

    How models behave inside an applied system and how to control that behavior.

    Stage outcomeA controlled LLM workflow with structured outputs, context management, and model routing.
    Materials ready
    Article →Article →
    Materials ready
    Prerequisites: LLMs, tokens, context, and inference
    Article →
    Materials ready
    Prerequisites: Prompt and context engineering
    Article →Article →
    Materials ready
    Prerequisites: LLMs, tokens, context, and inference
    Article →
  3. 03

    RAG and knowledge systems

    Building systems that answer from owned data and verifiable evidence.

    Stage outcomeProduction-ready RAG with citations, evaluation, freshness, and access control.
    Materials ready
    Article →
    Materials ready
    Prerequisites: Embeddings and semantic search
    Article →
    Materials ready
    Prerequisites: Ingestion and chunking
    Article →
    Materials ready
    Prerequisites: Retrieval, hybrid search, and reranking
    Topic →
    Materials readyAssessment available
    Prerequisites: Citations, freshness, ACL, and observability
    Open practicum →Assessment rubric →Practicum →
  4. 04

    Agents and tool ecosystems

    Governed multi-step systems with tools, state, and human oversight.

    Stage outcomeAn agent with explicit state, permission boundaries, audit logging, and evaluation.
    Materials ready
    Article →
    Materials ready
    Prerequisites: Agent loop and planning
    Article →
    Materials ready
    Prerequisites: State and memory
    Topic →
    Materials ready
    Prerequisites: Agent loop and planning
    Topic →
    Materials readyAssessment available
    Prerequisites: State machines, handoffs, and multi-agent systems, MCP servers, clients, and authorization
    Open practicum →Assessment rubric →Practicum →
  5. 05

    Evaluation, safety, and quality

    Systematic verification of quality, safety, and regressions.

    Stage outcomeAn evaluation pipeline that blocks unsafe or weak releases.
    Materials ready
    Article →
    Materials ready
    Prerequisites: Evaluation datasets and test cases
    Topic →
    Materials ready
    Article →
    Materials ready
    Prerequisites: Metrics and model graders, Prompt injection, guardrails, and red teaming
    Practicum →
  6. 06

    Production AI systems and runtime operations

    Deployment, serving, observability, runtime evidence, model/provider change control, cost, reliability, and incident response.

    Stage outcomeAn AI system with SLOs, traceable runtime truth, governed model/provider changes, known-good rollback, and verified economics.
    Materials ready
    Topic →
    Materials ready
    Prerequisites: Serving, streaming, and batching
    Article →Resource →
    Materials ready
    Prerequisites: Tracing, SLOs, and production monitoring
    Resource →Resource →
    Materials ready
    Prerequisites: Runtime evidence and false-green prevention, Regression and release gates
    Article →Glossary →
    Materials ready
    Prerequisites: Serving, streaming, and batching
    Article →Article →
    Materials ready
    Topic →Glossary →
    Materials ready
    Prerequisites: Runtime evidence and false-green prevention, Model, prompt, retrieval, and provider change control
    Article →Article →
    Materials ready
    Prerequisites: Failure injection, failover, and reconciliation
    Article →Resource →
    Materials ready
    Prerequisites: Incident response and rollback, Privacy, secrets, and governance, Capacity, cost, and routing budgets
    Article →Resource →