Avatar

Kai | Deep Android Engineering Notes

Deep notes on Android Framework, performance, Jetpack Compose, Kotlin, on-device AI, and mobile engineering.

Deep Android Engineering Notes

Android engineering knowledge base cover

A searchable knowledge base for Android Framework internals, performance optimization, Jetpack Compose, Kotlin coroutines, on-device AI, CI/CD, and mobile architecture.

Topic Index

Writing

Isolated-Process Inference for Android On-Device AI

Use a separate Android process and AIDL to isolate model memory and native crashes while preserving reliable inference lifecycle management.

Android ARCore: SLAM, Environment Understanding, and Light Estimation

Build stable Android AR experiences by understanding ARCore tracking, planes and depth, light estimation, rendering timing, and Compose integration.

Observability for Android On-Device AI Inference

Trace each on-device inference, build multi-dimensional performance profiles, and detect production regressions across fragmented Android hardware.

Android Text Layout: StaticLayout, FontMetrics, and LineBreaker

Learn Android text layout internals, from StaticLayout and font metrics to LineBreaker strategies and custom View rendering.

Android Overlay Windows: Permissions, WindowManager, and Compatibility

Build reliable Android overlay windows across platform versions, with permission handling, touch behavior, and OEM compatibility guidance.

Android Storage Access Framework: DocumentsProvider and DocumentFile

Understand how SAF unifies local and cloud documents through content URIs, DocumentsProvider, URI grants, and DocumentFile.

Privacy-First On-Device AI on Android

Build privacy-aware Android on-device AI with data minimization, transparent decisions, and audit-ready engineering practices.

ONNX Runtime on Android: Export, Quantize, and Run Models

An end-to-end guide to ONNX Runtime for Android, from export and integration through INT8 acceleration and operator compatibility.

Android LiveData Internals and a Safe Flow Migration

Explore LiveData lifecycle behavior and stale-event pitfalls, then migrate incrementally to StateFlow and SharedFlow.

Deploying ExecuTorch Models on Android

A practical ExecuTorch path from native PyTorch export to `.pte` deployment on Android, including AOT delegates and runtime trade-offs.