← All Episodes
Episode 4·April 22, 2026·00:33:16
Episode 4: Scaling AI Infrastructure: From Backend Engineer to Platform & Infra
Show Notes
In this episode of Making Software, Carla sits down with Matteo Ferrando who does Platform and Infrastructure at Fal.ai, to explore the complex world of infrastructure and platform engineering.
Matteo shares his journey from backend engineering to architecting a leading generative media platform. The conversation dives deep into:
The "Two-Way Door" Framework: How to decide between building a quick MVP and a long-term scalable solution.Latency-Sensitive AI: The infrastructure challenges of serving audio and video models with millisecond precision.Backend vs. Infra: Matteo’s "controversial" take on what backend engineering really means in a startup environment.The Future of Coding: Why computer science fundamentals are more important than ever in the age of AI-assisted development.Whether you're an engineer looking to transition into platform roles or curious about the "how" behind generative AI platforms, this episode is packed with practical architectural insights.
Guest
Matteo Ferrando
Platform & Infra, fal.ai
Matteo is an Infrastructure and Platform Engineer at fal.ai, where he was one of the company's first hires. As the team has grown and pivoted through multiple directions, he has been at the core of the infrastructure — managing thousands of GPUs, the routing and scheduling layers, and the platform that powers fal.ai's scale. He also works closely with customers to understand their needs and architects the infrastructure solutions that bring new features to life.
Subscribe to Making Software