Google Developer Group - PoliMi

Not every problem needs an AI agent. Join us for a deep dive into building AI agents that actually make sense—going beyond the hype to understand when, why, and how to deploy intelligent systems effectively.

What You'll Learn:

• 🎯 When to use agents (spoiler: not for 2+2)—understanding the right problems for agentic AI
• 🏗️ Agent Design Kit (ADK): patterns and architectures for building robust agents
• 🔧 Agent types: from simple task automation to complex multi-agent orchestration
• 🐋 Local models with Ollama: integrating open-source LLMs into your agent workflows
• 🌐 Open-source stack: building production-ready agents without vendor lock-in

Format: This session combines theory and practice:

• 📊 Conceptual overview with slides
• 💻 Live demos and code walkthroughs
• 🛠️ Hands-on patterns you can apply immediately

Who Should Attend: Developers, ML engineers, and tech enthusiasts interested in practical AI development. Whether you're building your first agent or optimising existing systems, you'll leave with concrete strategies for purposeful AI deployment.
Prerequisites: Basic programming knowledge. Familiarity with Python and LLMs is helpful but not required.

***

Once the talk is over you can stay a bit longer for a networking session where you can chat, meet new people, and just have a good time. ✌️

Stop treating language models as black boxes. Join us to build your own LLM from the ground up—understanding every layer, every attention head, and every training step that brings an AI to life.

What You'll Learn:

• 🏗️ Transformer architecture: decoder blocks, attention mechanisms, and the building blocks of modern LLMs
• 🔄 From tokens to text: embeddings, RoPE (Rotary Positional Embeddings), and how models understand language
• 🎯 Training your own Gemma: implementing a complete training pipeline with PyTorch
• ⚡ Modern training practices: mixed precision, gradient accumulation, learning rate scheduling
• 🛠️ Beyond APIs: why building from scratch teaches you what no API documentation can

Format - Talk + Demo:

• 📊 Architectural deep-dive with visual explanations
• 🧪 Training demonstrations and inference examples
• 📦 Open-source stack you can take home and experiment with

Who Should Attend: Developers and ML practitioners who want to understand what's really happening inside language models. Whether you're tired of treating LLMs as magic or ready to customise models for specific needs, you'll leave with a complete understanding of the foundations.
Prerequisites: Python and basic ML concepts. PyTorch familiarity is helpful but we'll cover the essentials.

Plus, once the talk is over you can stay a bit longer for a networking aperitivo where you can chat, meet new people, and just have a good time. ✌️