AI Engineer Study Library

Study plans

Week-by-week plans through the library, built from the free resources and posts of Bashiri Smith and Melvin Vivas. Pick the one that fits your time. In the library app, the Study plans tab lets you tick items off; the ticks are saved in your browser and shared with the other tabs.

  1. 1-month plan: the fast track

    Build one portfolio project in four weeks: an assistant over your own documents that grows from a prompted LLM call to RAG, evals and tools, and ends as a deployed, traced API while you start applying.

    4 weeks · about 15 hours a week

    1. Week 1: LLMs, prompts and APIs
    2. Week 2: Embeddings and RAG
    3. Week 3: Evals, then tools and agents
    4. Week 4: Ship it and start applying
  2. 2-month plan: the standard path

    Eight weeks on one capstone, an assistant that answers questions about your own documents, from the foundations through RAG, agents, evals and deployment to a portfolio case study and the job search.

    8 weeks · about 10 hours a week

    1. Week 1: Roadmap and foundations
    2. Week 2: LLMs and prompting
    3. Week 3: Embeddings and vector search
    4. Week 4: RAG
    5. Week 5: Agents, tools and MCP
    6. Week 6: Evals and guardrails
    7. Week 7: Deploy, monitor, fine-tune
    8. Week 8: Design, portfolio, job search
  3. 3-month plan: the thorough path

    Twelve weeks through all sixteen topics on one project, an assistant over documents you know, that grows from a single LLM call into an evaluated, guarded and deployed RAG agent with a small fine-tuned router.

    12 weeks · about 8 hours a week

    1. Week 1: Map the role and plan
    2. Week 2: How neural networks learn
    3. Week 3: LLM fundamentals and APIs
    4. Week 4: Prompts and coding agents
    5. Week 5: Embeddings and vector search
    6. Week 6: RAG that holds up
    7. Week 7: Agents, tools and MCP
    8. Week 8: Evals and guardrails
    9. Week 9: Ship, trace and control cost
    10. Week 10: Fine-tuning and system design
    11. Week 11: Portfolio week
    12. Week 12: Job search and trends
  4. 6-month plan: from the ground up

    Twenty-four weeks for people starting with little programming: a month of software basics (Python, Git, SQL and APIs), then the 3-month plan's capstone, an assistant over documents you know, with extra weeks for a web front end, data pipelines, production RAG, agent frameworks, Docker, the cloud, Kubernetes, system design and forward-deployed work.

    24 weeks · about 8 hours a week

    1. Week 1: Map the role and plan
    2. Week 2: Python for AI work
    3. Week 3: Git, GitHub and SQL
    4. Week 4: APIs and a Python backend
    5. Week 5: How neural networks learn
    6. Week 6: LLM fundamentals and APIs
    7. Week 7: Prompts and coding agents
    8. Week 8: A web front end for AI apps
    9. Week 9: Data pipelines
    10. Week 10: Embeddings and vector search
    11. Week 11: RAG that holds up
    12. Week 12: Production RAG and RAG evaluation
    13. Week 13: Agents, tools and MCP
    14. Week 14: Agent frameworks: LangGraph and MCP servers
    15. Week 15: Evals and guardrails
    16. Week 16: Docker and CI/CD
    17. Week 17: Ship, trace and control cost
    18. Week 18: Cloud fundamentals and infrastructure as code
    19. Week 19: Kubernetes and monitoring
    20. Week 20: Fine-tuning and system design
    21. Week 21: System design: services, auth and scale
    22. Week 22: Forward-deployed engineering and talking to users
    23. Week 23: Portfolio week
    24. Week 24: Job search and trends

Unofficial: not affiliated with or endorsed by the creators. The order follows the learning path.