AI Engineer Roadmap Before 2027: Fundamentals, RAG, Agents, Ops, Evals

Bashiri Smith · Facebook reel · 2026-09-19 · 1:09 · 13,530 views · Open on Facebook

Topics: Start Here: Roadmaps & Strategy, Programming & ML Foundations, Retrieval-Augmented Generation (RAG) · Level: beginner

Summary

This is a quick roadmap for becoming an AI engineer. First, make sure you have software engineering basics. Next, learn how models work with Andrej Karpathy's Zero to Hero series. Then learn the four core parts of the job: RAG, agents, ops and evaluation. The video names free courses, two books and a focus on projects, and ends with a pitch for the creator's Skool community.

Key points

• Check your software basics first: you should be able to build a simple to-do app without AI.
• Learn what happens inside the model before chasing tools. Tools change every few months, but deep fundamentals keep you ahead.
• Watch Andrej Karpathy's Zero to Hero series on YouTube for model internals.
• The four core parts of the job: RAG, agents, ops (LLMOps) and evaluation.
• RAG: LangChain's RAG from Scratch series. Agents: a Hugging Face course. Ops: an IBM video plus a DeepLearning.AI course.
• Books: Chip Huyen's 'AI Engineering' and Michael Albada's 'Building Applications with AI Agents'.
• Projects are the most important part. Build practice projects first, then your own personal project.

Resources mentioned

• Neural Networks: Zero to Hero (Andrej Karpathy) · course · karpathy.ai · free
  Build GPT from scratch. The guide calls it the deepest free foundation.
  Also in: AI Engineer Roadmap: Fundamentals, RAG, Agents, Books & Your First AI Service (Bashiri Smith on Facebook · notes)
• RAG From Scratch (LangChain) · video · github.com · free
  LangChain's free video series and notebooks that build retrieval-augmented generation step by step, from indexing through retrieval and generation.
  Also in: AI Engineer Roadmap: Fundamentals, RAG, Agents, Books & Your First AI Service (Bashiri Smith on Facebook · notes)
• Hugging Face Agents Course · course · huggingface.co · free
  A free agents course with a real completion certificate.
  Also in: AI Engineer Roadmap: Fundamentals, RAG, Agents, Books & Your First AI Service (Bashiri Smith on Facebook · notes)
• Large Language Model Operations (LLMOps) Explained (IBM Technology) · video · youtube.com · free
  An IBM explainer video on running and operating LLM applications (LLMOps). The exact title was shown on screen only.
• LLMOps (DeepLearning.AI) · course · learn.deeplearning.ai · free
  A DeepLearning.AI course on putting LLM applications into production. The exact course was shown on screen only. Free with a DeepLearning.AI account during its platform beta; certificates are paid.
• AI Engineering: Building Applications with Foundation Models (Chip Huyen) · book · github.com · paid
  Essential for AI engineers, even if some topics may not cover the newest tools. Good to know for ML engineers who want to build products with their models.
  Also in: 5 Books to Move from Software Engineer to AI/ML Engineer (Bashiri Smith on Facebook · notes), AI Engineer Roadmap: Fundamentals, RAG, Agents, Books & Your First AI Service (Bashiri Smith on Facebook · notes)
• Building Applications with AI Agents (Michael Albada) · book · oreilly.com · paid · open in a browser to verify
  Michael Albada's O'Reilly book on designing and building agent-based applications.
  Also in: AI Engineer Roadmap: Fundamentals, RAG, Agents, Books & Your First AI Service (Bashiri Smith on Facebook · notes)
• BASWE.Ai Engineer (Skool community) · community · skool.com · paid
  The creator's paid community and program, with an AI learning roadmap (including the full ops and evaluation track), daily calls with engineers and recruiters, resume and portfolio help, and a job-search pipeline.
  Also in: Basic RAG Pipeline in 60 Seconds: From Documents to Grounded Answers (Bashiri Smith on Facebook · notes), Pointer to Bashiri Smith's Complete AI Engineer Roadmap for 2026 (Bashiri Smith on Facebook · notes), Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), How to Evaluate a RAG Pipeline: Retrieval vs. Generation (Interview Answer) (Bashiri Smith on Facebook · notes) and 76 more

Try this

• Check your software fundamentals by building a basic to-do app without AI.
• Watch Andrej Karpathy's Zero to Hero series to learn how models work.
• Watch LangChain's RAG from Scratch series and build a RAG pipeline.
• Take the Hugging Face agents course.
• Watch the IBM LLMOps video and take the DeepLearning.AI ops course.
• Study evaluation resources (the video doesn't name them).
• Read Chip Huyen's 'AI Engineering' and Michael Albada's 'Building Applications with AI Agents'.
• Build practice projects, then design and build your own personal project.
• A basic to-do app built without AI, as a check of your software fundamentals
• A RAG pipeline built from scratch
• Your own personal AI project after doing the practice projects