Motorola Solutions

Overview of job

We are seeking a Principal Architect to define and own the architecture of our Unified Edge AI Engine. In this role, you will design the software backbone that orchestrates the entire lifecycle of video analytics on embedded hardware.

You will act as the bridge between Systems Engineering and AI Research. Your mission is to build a modular, graph-based execution engine that balances massive data throughput with limited compute resources, enabling advanced AI models (optimized via quantization/pruning) to run in real-time across diverse hardware platforms.

Scope of Responsibilities/Expectations:

• Pipeline Engine Architecture: Architect a modular, high-throughput Video & AI Pipeline Engine. Design the framework for dynamic graph construction (DAG) where AI models, logic nodes, and image processing blocks can be assembled and executed efficiently.
• Heterogeneous Resource Orchestration: Design the scheduling logic to balance workloads across CPU, GPU, DSP, and NPU. manage critical system bottlenecks such as PCIe Bandwidth, Memory Bandwidth, and Thermal constraints to prevent system stalls.
• AI Optimization Strategy: Define the architectural support for Model Quantization (INT8/FP16) and Network Pruning. Ensure the engine can natively handle optimized model formats, managing the trade-off between inference speed, memory footprint, and accuracy.
• Memory & Data Flow Design: Architect zero-copy data transport mechanisms (DMA, Shared Memory, Ring Buffers) to pass high-resolution video frames and tensor data between pipeline stages without CPU intervention.
• Scalability & Abstraction: Create a hardware-agnostic Abstraction Layer (HAL) that allows the engine to scale from low-power cameras to high-performance AI processors with minimal code changes.