Android Systems & Edge AI Engineer

I build Android systems and explore AI at the edge.

I'm Shubham Singh Bisht, an Android engineer based in Bengaluru. Currently building high-performance system software and interactive displays at Teachmint (ex-Pratilipi), with a focus on runtime internals, low-latency graphics, and on-device AI.

Android SystemsKotlinLarge ScreensPerformanceEdge AI

Selected work

A few things I've built, investigated, and learned from.

  1. 01 / 04

    Large-Screen Android Systems

    Android · Large screens · Hardware

    Building high-performance drawing systems and custom Android layers for large-screen interactive touch displays.

    Read case study
  2. 02 / 04

    On-Device AI

    AI / Edge · Embedded Systems

    Practical SLM inference and hardware-accelerated model deployment on constrained Android hardware.

    Read case study
  3. 03 / 04

    Android RAG

    AI / Edge · Vector Search · SQLite

    Building an entirely on-device Retrieval-Augmented Generation pipeline for educational content on Android.

    Read case study
  4. 04 / 04

    Cross-App Android SSO

    Android · Identity · IPC Architecture

    Designing a robust shared account and identity synchronization layer across multiple standalone apps on dedicated Android hardware.

    Read case study

Writing

Notes on Android, Kotlin, systems, and things I'm trying to understand.

  • 4 min read

    Building RAG on Android

    Why local retrieval-augmented generation is hard on a tablet, and how the pipeline is actually put together.

    #android#ai#rag#edge computing

  • 4 min read

    How Coroutine Dispatchers Actually Work

    Dispatchers.IO is not a pool of IO threads. What the CoroutineScheduler really does, and the mental model that replaced mine.

    #kotlin#coroutines#android#concurrency

03

A little more about me

Based in Bengaluru, I focus on the intersection of Android runtime systems, large-screen hardware displays, and edge intelligence. From scaling consumer mobile applications to engineering low-latency systems on dedicated touch hardware, I care about understanding how software works underneath the abstractions.

More about my background & approach