Staff Embedded ML/DSP Systems Engineer (Audio Engineering)
Core
Architect and optimize end-to-end deployment pipelines for compact audio AI models on DSP/NPU targets for real-time applications in industrial automation, data centers, communications, and hardware design.
Role type
Staff AI/ML Embedded ML/DSP Systems Engineer (Audio Engineering)
Builds
Scalable, production-grade audio AI systems for hearable/wearable devices, automotive, and industrial automation.
Domain
Semiconductor, Audio Signal Processing, Embedded AI, Physical AI
Deliverable
production ML models
Required skills
Fixed-point algorithm implementation, Model quantization (PTQ/QAT), Cycle-level optimization, Simulation-to-RTL flows, C (embedded/firmware), Python, MATLAB, Deep learning frameworks (TensorFlow/TFLite, Pytorch/ONNX), Low-level profiling, Instruction set architectures, Memory optimization
Preferred skills
NPU/accelerator architectures programming, ASIC development cycles, Always-on sub-mW audio processing, Patents in audio signal processing, Technical team leadership, Array signal processing, Beamforming, Acoustic system design
Technologies
DSP, NPU, SoC, TensorFlow, TFLite, PyTorch, ONNX, MATLAB, Python, C
Responsibilities
Architect and optimize deployment pipelines for audio AI models; Define DSP/NPU partitioning strategies; Own simulation-to-RTL validation flows; Implement and optimize signal processing and neural network kernels; Profile and optimize inference performance; Design model compression workflows; Develop signal processing algorithms for array processing and beamforming; Contribute to audio ASIC system architecture; Generate IP and represent technical depth to customers; Mentor engineers in deployment best practices.
Seniority
Staff, hands-on IC with mentorship
