Embedded Linux + C/C++ + Python

Title: Embedded Linux + C/C++ + PythonLocation: Irving, TXSkills: C++RolePort and optimize a containerized video analytics pipeline to run on CPU-constrained router hardware (Cradlepoint OS, Wi-Fi 7 PrplOS, FWA routers). You'll own the full stack: model optimization, container architecture, and on-device inference performance.What You'll DoPort GPU-based video analytics models (object detection, classification) to CPU-only router targetsOptimize inference pipeline to stay under 100MB memory footprint using SLMsBuild containerized architecture with dynamic cloud-driven model loadingTune accuracy/performance tradeoffs on ARM/MIPS router hardwareIntegrate with Cradlepoint OS and PrplOS environmentsBenchmark and iterate on detection accuracy vs. latency on constrained hardwareRequired4+ years in embedded systems or edge ML deploymentExperience with containerization (Docker, LXC) on constrained devicesML model optimization: quantization, pruning, ONNX, TensorFlow Lite, OpenVINOVideo analytics / computer vision (YOLO variants, object detection pipelines)Python + C/C++ on Linux embedded targetsCross-compilation, profiling, and memory optimizationStrong PlusCradlepoint NetCloud / PrplOS / OpenWRT experienceNPU/DSP acceleration on router-class SoCsDeepStream or similar inference pipeline experience (GPU→CPU migration)SLM deployment (sub-1B parameter models on edge)RTSP/video streaming on embedded LinuxYou AreComfortable with no GPU — CPU-only inference is the constraint, not a fallbackPragmatic about accuracy tradeoffs at the edgeExperienced navigating vendor OS lock-in and limited debugging toolchains