Rivu Chakraborty

Android & Kotlin GDE, Author, Speaker, Community Person

Rivu Chakraborty is an Android GDE (Google Developer Expert) and India's first Kotlin GDE, a community person, & one of the early adopters of Kotlin. With overall 13+ years of experience, he is currently running Mobrio Studio (https://mobrio.studio). He has previously worked with the biggest organisations from India and South-East-Asia, his last stint was working at JioHotstar / JioCinema (India's biggest OTT+Streaming platform) as Mobile Architect / Principal Engineer, he also previously worked at Meesho (a leading unicorn E-Commerce Startup from India), Gojek (one of South-East Asia's biggest startups), Paytm (India's biggest Fintech startup), and Byju's (one of India's biggest Edtech startup). He has contributed to multiple Kotlin and Android Development books including authoring Reactive Programming in Kotlin, co-authoring Functional Kotlin the first-ever book to help Kotlin developers learn Functional Programming and use Arrow-kt in their projects, and co-authoring Hands-On Data Structures and Algorithms with Kotlin. He has been using Kotlin since December 2015. Rivu formed KotlinKolkata User Group, the first active Kotlin User Group in India. Before he had to move out of Kolkata, he was organizing meetups and events for both KotlinKolkata and GDG Kolkata. Along with organizing community & events, he also speaks at events/conferences and local meetups.

Agents in Kotlin: Building High-Performance Intelligent Apps with Koog and Gemini

Kotlin Multiplatform showed us how to share logic. The next frontier is making that shared logic intelligent — and keeping it fast. This advanced session dives deep into how AI agents integrate within modern Kotlin-based Android architectures using Koog, Gemini Nano, and Vertex AI. We’ll explore how to run agents safely and efficiently across Android, iOS, and backend targets — with a strong focus on runtime performance, profiling, and observability. You’ll see how to design and tune agent lifecycles, optimize coroutine-based concurrency for background inference, and measure real-world behavior when running MediaPipe GenAI models locally. We’ll cover how to analyze (profiling) CPU and GPU utilization, memory pressure, and thread contention when agents are reasoning offline — and how to interpret those traces to find bottlenecks in on-device inference. We’ll close with production-ready strategies: structured fallback hierarchies, adaptive inference pipelines, and system-level optimizations that help AI-driven Kotlin apps remain responsive, energy-efficient, and scalable in real-world conditions. By the end, you’ll walk away with a deep understanding of how to embed, measure, and optimize intelligence directly inside your Android codebase — not just integrate it.