Staff Embedded ML Engineer, Edge AI

The role

You will lead on-device inference and performance optimization of ML models for outdoor monitoring. You will work across the stack to deliver reliable real-time behavior on embedded hardware like outdoor cameras and doorbells.

What you will do

• Own embedded deployment and performance of on-device ML inference for outdoor monitoring workloads.
• Optimize end-to-end inference performance across CPU, DSP, NPU, and GPU.
• Perform kernel and operator-level optimization including vectorization and memory layouts.
• Integrate and maintain ML models within embedded pipelines.
• Drive quantization and deployment readiness from an embedded perspective.
• Build tooling for profiling, benchmarking, and regression tracking on devices.
• Partner with ML engineers to translate model changes into deployment impact.
• Provide Staff-level leadership through technical reviews, mentoring, and setting performance standards.

Required qualifications

• 8+ years of experience in embedded systems and/or performance engineering.
• Experience shipping production software on constrained devices.
• Strong C/C++ expertise with knowledge of CPU architecture, memory hierarchy, concurrency, and real-time considerations.
• Demonstrated experience optimizing ML inference on embedded targets.
• Familiarity with modern vision model families such as transformer-based detectors (DEIM/DFINE/RT-DETR series) and CNN-based detectors (YOLO family).
• Experience with on-device inference runtimes and deployment workflows (e.g., TFLite, ONNX Runtime, TensorRT or vendor runtimes).
• Strong debugging and profiling skills (perf, flame graphs, hardware counters, tracing).
• Ability to lead cross-functionally across ML, firmware, and hardware teams.

Nice to have

• Experience with embedded accelerators and vendor toolchains (DSP/NPU compilers, delegates, GPU compute, custom runtimes).
• SIMD expertise (ARM NEON/SVE), hand-tuned kernels, or experience with libraries like XNNPACK/QNNPACK/oneDNN/CMSIS-NN.
• Experience with quantized inference (INT8) at scale.
• Experience with camera/doorbell pipelines: ISP/video decode/encode, DMA/zero-copy buffers, multi-threaded real-time streaming.
• Exposure to OS/firmware constraints (embedded Linux, RTOS), power management, thermal throttling behavior, and performance under sustained load.
• Security/privacy experience for edge devices (secure boot/TEE boundaries, model protection, safe telemetry).
• Experience building performance regression systems and device-lab automation for continuous benchmarking.

Benefits

• Comprehensive total rewards package.
• Free SimpliSafe system and professional monitoring for your home.
• Employee Resource Groups (ERGs).
• Annual bonus program.
• Equity.
• Medical, retirement, and lifestyle benefits.

About the company

SimpliSafe is a high-tech home security company with a no ego culture of collaboration and innovation.