Title: Senior Android Developer: Hybrid Computer Vision Pipeline (Local ML + Gemini API) Project Description: We are seeking a Senior Android Engineer to develop a modular, high-performance infrastructure for real-time video capture and analysis. The core of the project is a "Hybrid AI Routing Engine" that intelligently switches between on-device local processing and high-depth cloud analysis. This application is an R&D prototype that must be Play Store Ready, with a heavy focus on background stability, thermal management, and seamless connectivity transitions. Technical Specifications: 1. Camera Pipeline & Intelligent Routing: Implement CameraX to ensure maximum compatibility across various Android OEMs (Samsung, Pixel, Xiaomi, etc.). Develop a Routing Engine to ingest the camera stream and dispatch frames to two parallel modules: Offline Module: Local processing using ML Kit or TensorFlow Lite for immediate tasks (e.g., fast OCR, object proximity). Cloud Module: Optimized frame streaming (compressed JPEG/WebP) to the Google Gemini Flash API (target: 1-2 frames per second). 2. Smart Connectivity Fallback: Implement a robust network listener using ConnectivityManager / NetworkCapabilities. Automatic Failover: The system must detect low-latency or lost signals and instantly switch from Cloud mode to Local (Offline) mode without interrupting the user experience. Manual Toggle: A UI switch to force "Cloud-only" mode for maximum AI reasoning depth. 3. Performance & Thermal Management: Thermal Throttling: Implement logic to automatically scale down FPS or resolution if the device's thermal sensors reach critical thresholds. Foreground Service: Use a persistent Foreground Service with a custom notification to ensure the camera session remains active and is not killed by the Android OS during long-running sessions. 4. Real-time Audio Feedback: Integration of the native Text-to-Speech (TTS) engine to provide immediate audio descriptions of the processed visual data. Required Tech Stack: Language: Kotlin (Jetpack Compose for UI). Camera API: CameraX. On-Device AI: ML Kit or TensorFlow Lite. Architecture: Clean Architecture / MVVM (Modular approach is mandatory). Networking: Retrofit/OkHttp + Real-time connectivity monitoring. Deliverables: Fully documented, modular source code. Functional APK/AAB for internal testing. Setup for Google Play Console Internal Testing Track. Performance report (Battery impact and CPU/Thermal usage). Application Requirements (Filter Questions): To be considered, please answer the following technical questions in your proposal: 1.How do you plan to handle the synchronization between the camera buffer and the API call to prevent memory leaks? 2.Which strategy will you use to ensure the Foreground Service stays alive on "aggressive" OEMs like Huawei or Xiaomi? 3.Have you worked with CameraX extensions for Ultra-Wide lens selection? Please describe briefly.