Once, being a software developer required being a mathematician. As our ecosystem evolved, the field opened to a generation of problem-solvers who didn't need calculus to build world-class systems. Today, the AI revolution has polarized the field once again: separating those who understand complex math from those who simply call black-box APIs. But to build truly scalable, cost-effective, and performant enterprise applications, we cannot rely on "magic" alone. As the old engineering adage goes: you must understand at least two layers of abstraction below the one you are currently working in. This session bridges the gap between high-level prompt engineering and deep-dive data science by focusing on the architectural fundamentals of AI. We will demystify what models actually are as software artifacts, how they differ, and how they are executed via inference runtimes. You will learn to look at models through the lens of an engineer rather than a researcher, gaining the vocabulary to collaborate with data scientists and the technical depth to move beyond the API wrapper.

Talk Level:
INTERMEDIATE

Bio:
Milen is on a mission to help software developers worldwide design clean, modular, and future-proof systems. With over 25 years of experience building distributed architectures, consulting for global tech companies and leading engineering teams, he brings a "software craftsmanship" lens to modern development. While his roots are in enterprise Java and complex systems, Milen is currently focused on navigating companies and developers through the "AI ocean" without drowning. He is dedicated to ensuring they continue building well-architected solutions rather than falling for the newest shiny products.