Edge AI ML Engineer
Core
Develop, optimize, and deploy machine learning models for audio and multimodal intelligence on real-world edge devices, bridging ML modeling, DSP, and embedded systems.
Role type
Edge AI ML Engineer
Builds
Efficient neural networks and signal processing pipelines for embedded and on-device deployment
Domain
Audio technology, embedded systems, edge AI
Deliverable
production ML models
Required skills
C/C++ for embedded systems, machine learning model development and evaluation, model optimization for resource-constrained environments, Python for experimentation and tooling
Preferred skills
ML compilers and frameworks (MLIR, Glow, ExecuTorch), real-time streaming inference pipelines, acoustics and classical audio DSP, on-device ML (TinyML, quantization, pruning)
Technologies
FreeRTOS, CMake, TFLite Micro, ExecuTorch, MCUs, DSPs, NPUs
Responsibilities
Identify opportunities for new DSP/ML algorithms based on device constraints; Develop and iterate on audio and multimodal ML models for embedded applications; Convert trained models into efficient embedded implementations (C/C++, quantization); Optimize runtime performance for memory, latency, and power; Architect reusable embedded ML platform components; Profile and optimize performance on various hardware accelerators
Seniority
Mid-Senior, hands-on IC
