Five Core AI Engineering Topic Areas: A Study Roadmap Checklist

Bashiri Smith · Facebook reel · 2026-08-25 · 0:27 · 26,754 views · Open on Facebook

Topics: Start Here: Roadmaps & Strategy, Retrieval-Augmented Generation (RAG), AI Agents, Tool Use & MCP · Level: beginner

Summary

This short reel splits AI engineering study into five areas: LLMs & RAG, Agents & Orchestration, Ops & Evaluation, Safety & Ethics, and ML Foundations. The caption lists the subtopics for each area, and each area ends with a checkpoint project. The video itself names no tools, but the caption names LangGraph, MCP, scikit-learn, MLflow and DVC. The second half of the video promotes the creator's Skool community, which offers coaching.

Key points

• LLMs & RAG: LLM fundamentals, LLM APIs, embeddings and semantic search, vector databases, basic RAG, document processing and chunking, and advanced retrieval. Ends with a checkpoint project.
• Agents & Orchestration: function calling and tool use, structured outputs and validation, LLM frameworks, agent fundamentals, agentic design patterns, LangGraph orchestration, multi-agent systems, memory and state, agentic RAG, and MCP. Ends with a checkpoint project.
• Ops & Evaluation: LLMOps fundamentals, serving open-source models, deployment, observability and monitoring, CI/CD for LLM apps, evaluation fundamentals, LLM-as-a-judge, RAG evaluation, agent evaluation, and benchmarking models. Ends with a checkpoint project.
• Safety & Ethics: responsible AI, data ethics and bias, LLM security and risk, guardrails, and AI governance frameworks. Ends with a checkpoint project.
• ML Foundations: ML fundamentals and metrics, scikit-learn pipelines and model training, data engineering and quality, MLflow experiment tracking, DVC data versioning, deployment and CI/CD, and monitoring ML in production. Ends with a checkpoint project.
• The creator presents these five areas as the skills for AI engineering jobs paying $150,000 or more.
• Each area ends with a checkpoint project, so you build something to apply what you learned before moving on.

Resources mentioned

• LangGraph · tool · langchain.com · free
  Open-source library for building stateful LLM workflows as graphs, with branching, loops and human-in-the-loop pauses.
  Also in: Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), LangChain vs. LangGraph Explained with One RAG Chatbot (Bashiri Smith on Facebook · notes), Wannabe vs $200K+ AI Engineer: RAG, Agents, Context and Fine-Tuning Mistakes (Bashiri Smith on Facebook · notes), 7 Habits to Become an AI Engineer: Books, Tooling, Research & Shipping (Bashiri Smith on Facebook · notes) and 2 more
• Model Context Protocol (MCP) · docs · modelcontextprotocol.io · free · recommended by both Bashiri Smith & Melvin Vivas
  An open standard for connecting LLM apps and agents to tools and data sources. The official docs explain how it works and how to build servers and clients.
  Also in: Grok Bot Templates: Sharing, Publishing and Safely Installing Bots (Melvin Vivas on X · notes), 8-Week Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes), Paste Documentation URLs into Codex Instead of Using MCP (Melvin Vivas on X · notes), OpenAI Agents API: Hosted Codex Harness for Long-Running Cloud Agents (Melvin Vivas on X · notes) and 7 more
• scikit-learn · tool · scikit-learn.org · free
  A Python machine learning library for building pipelines and training classic ML models.
  Also in: Step-by-Step Roadmap to a $200K+ AI Engineering Role (Bashiri Smith on Facebook · notes)
• MLflow · tool · mlflow.org · free
  Experiment tracking and a model registry.
• DVC (Data Version Control) · tool · dvc.org · free · open in a browser to verify
  Version your data like code.
  Also in: 17-Step AI Engineer Roadmap: From Basic RAG to Agents, Evals, LLMOps & Governance (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

• Work through the subtopics of all five areas: LLMs & RAG, Agents & Orchestration, Ops & Evaluation, Safety & Ethics, and ML Foundations.
• Finish each area by building its checkpoint project.
• Optional: comment '90' or use the Skool link to join the creator's community for a personalized plan and coaching.
• LLMs & RAG checkpoint project: a RAG app that covers chunking, embeddings, a vector database and advanced retrieval.
• Agents checkpoint project: a LangGraph agent or multi-agent system with tool calling, memory and MCP.
• Ops & Evaluation checkpoint project: deploy an LLM app with observability and CI/CD, and evaluate it with LLM-as-a-judge.
• Safety & Ethics checkpoint project: add guardrails and security risk checks to an LLM application.
• ML Foundations checkpoint project: a scikit-learn pipeline with MLflow tracking, DVC data versioning, deployment and monitoring.