5 AI Engineer Skills Mapped to 5 Portfolio Projects
Bashiri Smith · Facebook reel · 2026-10-07 · 0:18 · 10,804 views · Open on Facebook
Topics: Portfolio Projects, LLMOps, Deployment & Monitoring, Evaluation (Evals) & Testing · Level: intermediate
Summary
Bashiri Smith matches five production-oriented AI engineering skills with one portfolio project each. The skills are LLM observability, cost optimization, multimodal AI, prompt engineering and AI regression testing. The caption describes each project, and it links to a Google Drive folder with 27 AI project ideas.
Key points
- LLM observability: build a failure forensics tool that traces a broken pipeline back to the exact step that failed.
- Cost optimization: build an LLM cost autopilot that sends each request to the cheapest model that can handle it (model routing).
- Multimodal AI: build a document processor that turns messy PDFs and scans into clean structured data.
- Prompt engineering: build a prompt versioning and A/B testing platform that shows which prompt actually performs better.
- AI regression testing: build a system that runs evals on every commit and blocks changes that lower quality (CI-gated evals).
- These projects focus on production concerns (tracing, cost, evals, CI) rather than basic chatbot demos.
Resources mentioned
- AI Projects (Google Drive folder) · pdf · drive.google.com · free
The creator's guide to 27 AI projects, with full architecture, build steps phase by phase, interview talking points, and the stack for each project.
Also in: Prompt Claude to Plan 3 Production-Grade AI Portfolio Projects (Bashiri Smith on Facebook · notes), 25 AI Engineer Interview Questions Covering ~95% of Interview Topics (Bashiri Smith on Facebook · notes), 6-Step Framework for Building AI Projects Target Companies Care About (Bashiri Smith on Facebook · notes), Generate Job-Worthy AI Project Ideas from Recent Research Papers + ChatGPT (Bashiri Smith on Facebook · notes) and 6 more
Try this
- Choose one of the five skills and build the matching project for your portfolio.
- Open the 27 AI projects Google Drive folder for more project ideas.
- Add evals to CI so every commit is checked for quality regressions.
- LLM failure forensics tool that traces a broken pipeline to the exact failing step
- LLM cost autopilot that routes each request to the cheapest capable model
- Multimodal document processor that turns messy PDFs and scans into structured data
- Prompt versioning and A/B testing platform
- AI regression testing system that runs evals on every commit and blocks quality drops
More in Portfolio Projects
- Creator shares his GitHub profile (donvito)
- Local Two-Person Video Face Swap: InsightFace + GFPGAN + SegFormer
- Generate Portfolio AI Project Ideas with Claude and Hugging Face Tasks
- Automating Insurance Receipt Claims with OCR and Jev
- 6 Production-Grade RAG Portfolio Projects Beyond "Chat with Your PDF"
- Melvin Vivas's GitHub Profile of AI Projects