Principal Architect (Engine Pipeline)

About the Role Principal Architect (Engine Pipeline) to architect a modular, high-throughput Video & AI Pipeline Engine for Motorola Solutions' R&D Center in Vietnam. You will design the dynamic graph (DAG) framework for assembling AI models, logic nodes, and image processing blocks, enabling efficient execution on edge devices. You will drive heterogeneous resource orchestration, AI optimization, and scalable memory/data flow across diverse hardware. What You'll Do

• 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 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 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. What We're Looking For
• System Architecture: Mastery of Modern C++ (14/17/20) and architectural patterns for high-concurrency, real-time systems. Deep understanding of Producer-Consumer models, Lock-free queues, and multi-threaded synchronization.
• AI Model Optimization: Strong knowledge of techniques to reduce model complexity: Quantization (PTQ/QAT), Weight Pruning, and Knowledge Distillation. Experience integrating these optimized models into C++ runtimes (e.g., TensorRT, SNPE/QNN, OpenVINO).
• Hardware Intimacy: Deep understanding of SoC architectures (Qualcomm, Ambarella, NVIDIA). Ability to analyze how Cache Coherency, Bus Arbitration, and Memory Controllers impact AI performance.
• Profiling & Analysis: Expert ability to use system profilers (e.g., Perf, eBPF, Nsight Systems) to visualize the "Critical Path" of the pipeline and optimize instruction-level performance.
• Pipeline Frameworks: Experience designing or heavily customizing media pipelines (similar to GStreamer, MediaPipe, or DeepStream).
• Education: Bachelor’s Degree or higher in Embedded AI, Computer Science, Computer Engineering, or related technical fields.
• Experience: 10+ years of industry experience in Embedded Software Architecture or High-Performance Computing. Proven track record of designing complex software engines for Video Processing, Computer Vision, or Autonomous Systems.
• Experience acting as a System Architect, making critical decisions on resource allocation, memory management, and hardware selection.