school

The AI Internship

AI Engineering Bootcamp

auto_awesome AI Engineering Bootcamp & Certificate

Building with AI, week by week

A portfolio of projects built during the AI Engineering Bootcamp. Each week tackles a new challenge — from multi-provider LLM gateways to production RAG pipelines.

auto_awesome Week 1: LLM Gateway menu_book Week 2: RAG Pipeline hub Week 3: Multi-Agent

Progress Timeline

check
Week 1 LLM Gateway
check
Week 2 RAG Pipeline
check
Week 3 Multi-Agent
auto_awesome

LLM API Playground

Live

Week 1 — Multi-provider LLM gateway with chat UI

A FastAPI-based LLM gateway supporting OpenAI GPT-4o Mini, Anthropic Claude Sonnet, and Google Gemini Flash. Features text summarization, sentiment analysis, interactive chat with conversation history, and prompt engineering with 3 strategy variants.

  • check Multi-provider LLM support (GPT-4o, Claude, Gemini)
  • check 3 prompt engineering strategies per endpoint
  • check Interactive chat with conversation history
  • check Sentiment analysis with confidence scoring
Python FastAPI OpenAI Anthropic Gemini SQLAlchemy
Launch App arrow_forward description API Docs
menu_book

RAG Document Q&A

Live

Week 2 — Interactive RAG pipeline over RL research papers

A full RAG system built over 10 reinforcement learning research papers. Features an interactive 6-step notebook, live Q&A chat with hybrid BM25 + vector search, dual evaluation (heuristic + LLM-as-judge), and one-click autoplay.

  • check Interactive 6-step RAG notebook
  • check Hybrid BM25 + vector search retrieval
  • check Dual evaluation: heuristic + LLM-as-judge
  • check One-click autoplay for full pipeline execution
Python FastAPI LangChain Ollama ChromaDB RAG
Launch App arrow_forward description API Docs
hub

Nexus Multi-Agent

Live

Week 3 — Multi-agent customer support with MCP & A2A

A multi-agent customer support system built with Google ADK. Features a root router that delegates to billing (MCP), returns (A2A), and escalation sub-agents with real-time streaming.

  • check Root router + 3 specialist sub-agents
  • check MCP integration with Supabase database
  • check A2A protocol for returns microservice
  • check Real-time SSE streaming with agent activity
Google ADK Gemini Supabase MCP A2A
Launch App arrow_forward description API Docs

Technologies Used

Python FastAPI LangChain Ollama ChromaDB OpenAI Anthropic Gemini SQLAlchemy Google ADK Supabase MCP A2A Protocol Tailwind CSS Docker Nginx