AI Phone - On-device AI
Core
Evaluate, benchmark, and integrate open-weight and commercially available ML models for on-device execution on mobile hardware.
Role type
Senior IC on-device AI inference engineer
Builds
Optimized local AI models and hybrid local/cloud routing mechanisms for Android applications
Domain
Mobile computing and edge AI
Deliverable
production ML models
Required skills
ML systems engineering, model inference optimization, Python, C++, neural network inference, model quantization, performance benchmarking, hardware constraints analysis
Preferred skills
on-device LLM deployment, mobile/edge AI, multimodal model optimization, Qualcomm QNN, MediaTek NeuroPilot, ONNX Runtime, LiteRT, TensorFlow Lite, ExecuTorch, Android NDK
Technologies
Android, CPU, GPU, NPU, Python, C++, ONNX Runtime, TensorFlow Lite, ExecuTorch, Qualcomm QNN, MediaTek NeuroPilot
Responsibilities
Evaluate open-weight and commercially available models for on-device execution; Benchmark model performance on target mobile hardware; Integrate models into Android applications and system services; Optimize inference latency, memory consumption, and power usage; Evaluate quantization, compression, and model distillation techniques; Work with CPU, GPU, and NPU acceleration; Build hybrid local/cloud model-routing mechanisms; Integrate local models into the agent runtime with AI agent engineers
