Mastering AI stacks for software engineers
Ai stack Llm inference Google io Software engineering Data center Agentic ai Hardware optimization Cloud infrastructure Token optimization Ai infrastructure
This Google I/O interview explores the five-layer AI stack for software engineers and cloud professionals, covering agentic coding frameworks at the application layer down to LLM inference engines and data center energy requirements. Caleb Eom discusses optimizing token generation speeds, understanding hardware constraints, and building data center-aware AI applications. Ideal for cloud engineers and systems architects looking to transition into AI-focused technical roles.
Related videos
The ABCs of agent building
From systems of intelligence to systems of action: Yasmeen Ahmad on the agentic data cloud
I've been pretty busy lately
Moving AI agents beyond “Hello World” to real production
Scaling multi-modal AI to 7 million users
Build full-stack apps with Google AI Studio, Cloud Run, and Cloud SQL
Agent-first workflows from prompt to production
The future of Cloud AI: Mastering MCP servers, Gemini, and agentic workflows
From the I/O main stage to the terminal
Context is the Key to the Agentic Architecture Revolution: A Conversation with Baruch Sadogursky
Is debugging an AI system fundamentally different than debugging a traditional software system?
