Arvind Kumar Vartiya

20 NOVEMBER 2026

BENGALURU

( SPEAKER )

AI Engineer & Agent Architect

KiKsAR Technologies

I'm a Computer Scientist and AI Engineer passionate about building intelligent systems that solve real-world problems. An IIT Kanpur alumnus, I specialize in Generative AI, Large Language Models, Agentic AI, and intelligent automation.

Currently, I work as a Forward Deployed Engineer (FDE), contributing to AI vision and agent architecture for Signature Aviation, one of the world's largest Fixed Base Operator (FBO) networks. My work involves designing and building intelligent, multi-agent systems that bring AI capabilities into complex, real-world aviation workflows.

My experience spans AI-powered voice and WhatsApp agents, multi-agent architectures, RAG systems, and real-time conversational AI. I work across technologies including LLMs, STT/TTS, LangGraph, MCP, and cloud AI platforms.

I'm particularly interested in the intersection of AI research and engineering — transforming emerging AI capabilities into reliable, scalable, production-ready systems that can reason, interact, and take meaningful actions in the real world.

Lightning talk

MCP Servers on Android: Turn Any App into an AI Agent Tool

AI agents are only as powerful as the tools they can call. On desktop, MCP (Model Context Protocol) lets AI assistants interact with local apps, reading files, querying databases, and sending messages. But on Android? There's no standard way for an AI agent to discover and call tools from other installed apps on the same device. This session introduces a lightweight approach to building on-device MCP servers inside Android apps using HTTP semantics over Binder IPC. No internet. No cloud APIs. No exposed network ports. Just fast, secure, inter-app communication that lets any AI assistant discover your app's capabilities and invoke them — all without data ever leaving the device. I'll live-code an MCP server that exposes tools (like searching contacts or sending messages) as a bound Android Service, and show how an AI agent app can discover, connect, and call those tools at runtime, the same way it would call a cloud MCP server, but entirely on-device.