Applied ML Engineer - Edge Devices

What you'll do

• Adapt model structures, operators, and precision for edge hardware while maintaining accuracy and latency.
• Benchmark ports on real devices and build repeatable model conversion, packaging, and deployment workflows.
• Coordinate with embedded engineers and platform or silicon vendors to make models work with target kernels, runtimes, and toolchains.

What they ask for

• Production experience deploying ML models to edge or non-NVIDIA hardware; cloud-only or GPU-only serving experience does not qualify on its own.
• Working knowledge of quantization and precision tradeoffs, including INT8, FP16, mixed precision, and calibration.
• Experience with an edge or vendor inference runtime and its conversion toolchain; ability to modify model graphs, operators, and architecture parameters.
• Strong Python and PyTorch, production-quality testing and benchmarking habits, and comfort automating model conversion and deployment.

Nice to have

• Experience with speech, audio, or streaming/real-time models.
• Exposure to low-level kernels, deployed-model security, multiple accelerator families, or internal porting tools.

Pay

$155K – $245K (base salary); 10% Annual Bonus (bonus)

Tools

ONNX Runtime, TFLite, ExecuTorch, OpenVINO, Qualcomm AI Engine, Python, PyTorch, CUDA

AI focus

Apply AI tools in everyday work and experiment with advanced AI capabilities; the role itself focuses on deploying speech models to edge hardware.