Event

FREE data + AI knowledge sessions to help each others and learn from each other, share job opportunity

Session 6: LLMs Deep Dive — Routing, Cost Control & Building a Multi-Model System
Gemini, GPT, Claude, Llama, Qwen — when to use which, and how to build a system that switches between them automatically.
Demo (~15 min): Show an LLM router — change provider live, restart, compare quality and cost. Per-user token budgets. GCP Vertex AI model garden. Ollama ($0) vs Gemini ($0.075/1M) vs GPT ($2.50/1M).
AI Hands-on (~15 min): Live model shootout. Same complex prompt to 4 models simultaneously (Gemini Flash, GPT-4o, Claude Sonnet, local Qwen). Group scores each response on accuracy, speed, cost. Build a mental model of which model to reach for in different situations.
Open Floor (~20 min): Which models are you using and for what? Fine-tuning vs prompting — was it worth it? Monthly LLM spend and how you control it? What tasks does AI still do badly despite the hype?

***

| Session | Special Topic | AI Component |
| ------- | ------------- | ------------ |
| 1 | Data & AI Ecosystem overview | First prompt challenge — everyone builds something |
| 2 | Cloud Infrastructure (AWS/GCP/Snowflake) | Vibe-code a Dockerfile + docker-compose with AI |
| 3 | Data Pipelines & Quality | AI anomaly detection on messy data |
| 4 | Analytics & BI | Text-to-SQL — ask your database in English |
| 5 | ML Evaluation & Backtesting | AI as model critic — "what's wrong with my eval?" |
| 6 | LLMs Deep Dive | Live model shootout — 4 models, same prompt, group scores |
| 7 | AI Agents — Tools, RAG, Memory | Vibe-code a working agent together |
| 8 | Multi-Agent Systems | Group design exercise — sketch a multi-agent for your problem |
| 9 | Vibe Coding Deep Dive | Build a complete feature live with AI |
| 10 | Show-and-Tell & Opportunities | Community demos + jobs + what's next |