Sasha Denisov
Brainform.ai, CTO, Cloud.AI, Flutter, Dart and Firebase GDE
Sasha is CTO at Brainform.ai with over 20 years of experience architecting scalable enterprise systems. With a strong engineering background, his expertise spans frontend, backend, cloud infrastructure, mobile development, and AI — from cloud-based generative AI to on-device solutions. He specializes in building robust, production-ready products using a variety of technologies and frameworks. Sasha has delivered solutions across fintech, digital media, and entertainment. He is a Google Developer Expert for Cloud, AI, Firebase, Flutter, and Dart, co-organizes the Flutter Berlin Community, and is a recognized international speaker and writer, having presented at 30+ conferences worldwide.
Evolution of flutter_gemma: From a Simple Wrapper to a Cross-Platform AI Engine
flutter_gemma started as a thin MediaPipe wrapper for running Gemma on Android and iOS. Today it's a full on-device AI platform: 6 platforms, 2 inference engines, multimodal support, function calling for local agents, and on-device RAG with vector search — featured by Google at I/O 2026.
This talk walks through that evolution via real engineering decisions. How adding Web forced sealed classes over string URLs. How desktop went from a Kotlin/JVM gRPC server to running LiteRT-LM directly via dart:ffi — dropping a bundled JRE and cutting engine startup from ~15s to ~2s. How the Strategy and Adapter patterns let us add a second engine without a rewrite. How we built on-device RAG on a Qdrant vector store that runs identically on mobile and in-browser via WASM. Plus real bugs and fixes, from Web hot-restart crashes to iOS Simulator vision-model limits.
Minimum theory, maximum code, diagrams, and stories of how it broke and why it looks like this now.