AI Engineering Portfolio Projects

Build hands-on AI engineering projects that show how you design, test, and ship useful AI systems. The guides include a project roadmap, recommended tools, and ways to explain your work to employers.

Career areas

• AI Engineer
• Machine Learning Engineer
• Applied AI Engineer

Browse AI Engineer projects

• Multi-Agent Research & Execution System

  A collaborative AI system where specialized agents (Researcher, Writer, Fact-Checker) work together to autonomously generate reports.

  Level: intermediate · Tools: CrewAI, LangGraph, Python, OpenAI/Claude API

• Multimodal RAG for Enterprise Knowledge

  A Retrieval-Augmented Generation pipeline that handles documents with text AND images — charts, tables, diagrams.

  Level: advanced · Tools: LlamaIndex, Pinecone, Python, Claude 3.5

• AI-Powered Code Reviewer Bot

  A GitHub Actions bot that auto-reviews pull requests for style, bugs, and security issues — suggesting refactors.

  Level: intermediate · Tools: GitHub Actions, Python, OpenAI API, SonarQube

• AI-Powered Self-Service IT Support Bot

  An intelligent chatbot using RAG to answer IT questions from a knowledge base — with fallback ticket creation.

  Level: intermediate · Tools: Botpress/Voiceflow, OpenAI API, Google Sheets, Zapier

• Multi-Agent Autonomous Research System (Supervisor Pattern)

  A system where AI agents (Researcher, Writer, Fact-Checker) collaborate under a Supervisor agent that manages workflow.

  Level: advanced · Tools: Python, LangGraph, Tavily, Claude 3.5

• Automated Customer Support AI Agent

  A no/low-code AI agent that ingests support tickets, drafts responses, and routes complex issues — your first end-to-end agentic workflow.

  Level: beginner · Tools: OpenAI Agent Builder, Zapier, n8n, OpenAI GPT models

• Build an MCP Server for Your Own Data

  A Model Context Protocol server that exposes your own data — a SQLite database, a folder of notes, a small API — as tools that Claude Desktop and Claude Code can call directly. Your first real bridge between an LLM and a live system.

  Level: beginner · Tools: Python, MCP Python SDK, FastMCP, SQLite

• Cost-Aware LLM Model Router

  A gateway that classifies every incoming request by difficulty and sends the easy ones to a cheap, fast model and the hard ones to a frontier model — then proves the savings with a dashboard built from a real query log.

  Level: intermediate · Tools: Python, FastAPI, LiteLLM, Claude Haiku + Claude Opus

• Agent Evals and Trace Observability Harness

  A regression-testing and tracing system for an AI agent — every run captured as a trace with tool calls and reasoning steps, scored against a golden dataset, and gated in CI so a prompt change that breaks behavior fails the pull request.

  Level: advanced · Tools: Python, LangSmith or Langfuse, DeepEval, OpenTelemetry

• AI Experiment Lab: Compare Prompts and Models on Real Job Posts

  A small, repeatable experiment that runs several prompts and models against the same set of job descriptions, checks whether each one correctly spots real entry-level roles, and reports which did best on accuracy, speed, and cost. Inspired by the experiment loop in Andrej Karpathy's autoresearch: change one thing, measure it, keep what works.

  Level: beginner · Tools: Python, Claude or OpenAI API, Ollama (free local model), pandas