Principal Architect (Engine Pipeline)

Motorola Solutions
Vietnam
Workplace: OnsiteFull timeFunction: Software EngineeringExperience: 10+ yearsEducation: bachelorsSkills: []

Senior software architect focused on building a modular, high-throughput Video & AI Pipeline Engine for edge devices. You will design DAG-based graphs, heterogeneous resource orchestration, AI optimization strategies, and a hardware-agnostic HAL to scale from low-power cameras to AI processors, aligning with Motorola Solutions' AI hub in Vietnam.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Motorola Solutions
Motorola Solutions
4 months ago

Principal Architect (Engine Pipeline)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 15 days agoStatus: Live

Job Summary

Senior software architect focused on building a modular, high-throughput Video & AI Pipeline Engine for edge devices. You will design DAG-based graphs, heterogeneous resource orchestration, AI optimization strategies, and a hardware-agnostic HAL to scale from low-power cameras to AI processors, aligning with Motorola Solutions' AI hub in Vietnam.
Location: Vietnam
Workplace: Onsite
Employment Type: Full time
Job Function: Software Engineering

Key Responsibilities

  • •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.
  • •Design the scheduling logic to balance workloads across CPU, GPU, DSP, and NPU; manage PCIe Bandwidth, Memory Bandwidth, and Thermal constraints to prevent system stalls.
  • •Define the architectural support for Model Quantization (INT8/FP16) and Network Pruning; ensure the engine can natively handle optimized model formats with trade-offs between inference speed, memory footprint, and accuracy.
  • •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.
  • •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.

Key Requirements

  • •Mastery of Modern C++ 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: Quantization (PTQ/QAT), Weight Pruning, Knowledge Distillation; experience integrating optimized models into C++ runtimes (e.g., TensorRT, SNPE/QNN, OpenVINO).
  • •Hardware Intimacy: Deep understanding of SoC architectures (Qualcomm, Ambarella, NVIDIA); analyze how Cache Coherency, Bus Arbitration, and Memory Controllers impact AI performance.
  • •Profiling & Analysis: Proficient with system profilers (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 (e.g., GStreamer, MediaPipe, DeepStream).
Experience:10+ yearsEmbedded softwareAiEdgeVideo processingComputer vision
Education:Bachelor's in Embedded AI, Computer Science, Computer Engineering
Tech Stack:C++TensorRTOpenVINOSNPE/QNNGStreamerMediaPipeDeepStreamCUDAPCIeDMANsight SystemsPerfEBPF

Company Brief

Motorola Solutions
Provides mission-critical communications products and services, including radios, software, video security, and command center solutions for public safety, government, and enterprise customers worldwide.
Industry: Surveillance & Security Hardware
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Public Company
Valuation: Public Company (Market Cap in USD)
Funding: IPO / Publicly Listed
Headquarters: Chicago, United States
Founded: 1928
Glassdoor
Glassdoor: 3.7
WebsiteLinkedIn