Learn AI Engineering by Building One Project per Skill

Bashiri Smith · Facebook reel · 2026-09-09 · 0:22 · 25,126 views · Open on Facebook

Topics: Portfolio Projects, Start Here: Roadmaps & Strategy · Level: intermediate

Summary

Bashiri Smith says you should stop learning AI concepts without building anything with them. Instead, build one real project for each core AI engineering skill: RAG, agents, evals, ops, security and machine learning. He links a free Google Drive guide with 27 projects like these, plus his AI engineering community of working AI engineers and recruiters.

Key points

• Don't just study AI concepts. Turn each skill into a project you actually build.
• RAG: build a retrieval-augmented generation pipeline that uses hybrid search.
• Agents: build an agent orchestration system that coordinates multiple agents.
• Evals: build a generator that creates eval sets from production logs.
• LLMOps: build a semantic caching layer.
• Security and guardrails: build a SQL guardrail layer that blocks destructive queries.
• ML foundations: build a fine-tuning pipeline that uses LoRA.
• The creator's guide has 27 projects like these, and the caption links to it.

Resources mentioned

• AI Projects (Google Drive guide) · pdf · drive.google.com · free
  The creator's Google Drive folder with a guide to 27 AI engineering portfolio projects, organized by skill.
• 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

• For every AI skill you learn, build an actual project with it.
• Comment 'projects' on the video to get links to the project guide and the community.
• Work through the projects in the AI Projects Google Drive guide.
• RAG pipeline with hybrid search (retrieval-augmented generation)
• Multi-agent orchestration system
• Eval set generator built from production logs (LLM evaluation)
• Semantic caching layer (LLMOps)
• SQL guardrail layer that blocks destructive queries (AI security and guardrails)
• Fine-tuning pipeline with LoRA (ML foundations)