Lead Android Engineer @DearDhruv Battle-Tested Leadership

Dhruv Patel

Android Architect · Android Artist · On-Device AI

I'm a Lead Android Engineer, Android Architect, and Android Artist (known online as @DearDhruv). I work on the parts of software that get interesting when they hit real device constraints: performance profiling, low-level hardware interfaces, and running local AI models on personal devices without cloud dependencies.

Explore Portfolio Featured Projects AI Engineering Series Résumé (PDF)

Engineering Domains

Specialization & Technical Focus

The technical areas where I spend most of my time, from native Android internals to cross-platform runtimes and low-level device hardware.

Domain 01 Battle-Tested

Android & Native Architecture

Production Clean Architecture, unidirectional data flow (MVI/MVVM), Jetpack Compose, modular multi-module codebases, memory profiling, and battery guardrails.

Kotlin Jetpack Compose Coroutines/Flow NDK / C++20

Explore Architecture

Domain 02 Production

Kotlin Multiplatform (KMP/CMP)

Cross-platform architecture sharing deterministic game loops, MVI state stores, and offline-first persistence across Android, iOS (SwiftUI host), and Android TV.

Compose Multiplatform SQLDelight Cloud Firestore Swift Interop

Explore Projects

Domain 03 Offline-First

On-Device AI & Edge Compute

Local LLM inference and on-device diffusion studios (llama.cpp, LiteRT, Apple MLX) running on consumer phones with speculative drafting and defensive driver crash sandboxing.

Image Generation llama.cpp Google LiteRT Apple MLX Stable Diffusion Vulkan / Metal

Explore AI Series

Domain 04 Enterprise

Commerce & Hardware Integration

Digital commerce flows, payment terminal protocols, and resilient hardware abstraction layers across 30+ POS peripherals with defensive IPC.

POS Peripherals Payment IPC HAL Bridges Zero Cloud Leak

Explore Systems

Featured Work

Selected Production Systems

Real-world applications and native libraries engineered for performance, resilience, and privacy.

System 01 Flagship · On-Device AI

AI Playground

An offline-first multimodal AI workstation that runs local LLMs and diffusion models directly on mobile silicon—keeping user conversations and documents private without cloud round-trips. Built with Kotlin Multiplatform, C++20 JNI bindings to llama.cpp, Google AI Edge LiteRT, and Apple MLX. Includes dual-model speculative drafting (2x speedup) and a native fork() sandbox to isolate Vulkan driver crashes.

KMP Compose MP Image Generation C++20 NDK llama.cpp Vulkan/Metal

Google Play Read Series

System 02 Flagship · Multiplatform Game

VelociHue

A fast-paced arcade action game engineered in Kotlin Multiplatform and Compose Multiplatform for Android, iOS, and Android TV. Runs at 60–120 FPS using a shared deterministic physics loop, conflict-free Cloud Firestore schema v5 sync with 3-way union merge, and 29 progressive achievements.

KMP Compose MP Cloud Firestore Android TV SDK 37

Google Play Case Study

View Full Portfolio & Case Studies

Engineering Series

Beyond the Model: AI Playground Engineering Series

A six-part architectural log documenting the realities of running local LLMs, image generation, and document processing directly on mobile hardware.

Part 1 of 6 10 min

Offline Local LLMs

Architecting offline-first mobile inference, setting up speculative drafting with smaller models, and managing VRAM limits on mobile silicon.

Architecture Read

Part 2 of 6 9 min

Offline Document Engine

How a simple 'attach file' button turned into an offline ingestion pipeline for 25+ formats using pure RFC 1951 Deflate and memory-mapped chunks.

Deflate / KMP Read

Part 3 of 6 10 min

Defensive Crash Isolation

Handling vendor Vulkan driver GPU segmentation faults by running inference inside a native fork() process sandbox with a 3000ms watchdog loop.

NDK / C++20 Read

Part 4 of 6 11 min

On-Device Diffusion Studio

Synthesizing 4-step diffusion images on mobile GPUs using Google LiteRT and Bonsai Image Ternary 4B without thermal runaway.

Diffusion AI Read

Part 5 of 6 12 min

Modular MVI Architecture

Refactoring a monolithic mobile app into a multi-module MVI platform with clean offline boundaries, strict state stores, and zero cloud leaks.

MVI / Clean Arch Read

Part 6 of 6 11 min

Pushing Hardware to the Edge

Engineering dual-model speculative drafting for 2x decoding speed, isolating GPU driver segmentation faults in a native fork() sandbox, and streaming fault tolerance.

Hardware Tuning Read

Read All 6 Series Articles

Connect & Collaborate · @DearDhruv

Get in Touch

Find me as @DearDhruv across developer networks, or reach out directly. Always glad to talk through native Android architecture, Kotlin Multiplatform systems, on-device AI runtimes, or upcoming technical speaking opportunities.

Send Email LinkedIn GitHub X (Twitter) Instagram Download Résumé (PDF)

Also on: Google Play about.me Hugging Face Medium Stack Overflow YouTube