Syarah · Mobile Software Engineer
A Middle East-based automotive platform.
- Conceived, planned, and delivered a lightweight, on-device ML car-photo classification system using a custom-trained 42-class MobileNetV3 LiteRT/TFLite model. Integrated it across bulk upload, image validation, and live camera workflows, significantly reducing photography time and human classification errors.
- Built a real-time Android VIN scanner using CameraX, LiteRT, and ML Kit, with a lightweight custom-trained quantized detector and a complex VIN recognition algorithm covering OCR validation, checksum repair, and character-confusion recovery.
- Worked on an in-house camera SDK for vehicle data entry, image capture, and damage documentation during inspections, incorporating machine learning to identify which part of the car was being photographed.
- Developed a reliable in-house upload manager and SDK designed to remain resilient under unstable network conditions and extreme heat, substantially reducing image loss during transfers.