Audio AI Research Scientist — Audio Understanding
Core
Develop novel AI-powered audio processing algorithms for real-time deployment on physical devices to enable context understanding, dynamic awareness, and augmented hearing.
Role type
Research Scientist (Audio AI)
Builds
Real-time audio understanding models for consumer audio devices and automotive applications.
Domain
Audio technology / Machine Learning
Deliverable
production ML models
Required skills
Audio understanding models (SELD, acoustic scene analysis), Deep Learning (PyTorch), Python, DSP, Data pipeline construction, Multimodal fusion
Preferred skills
Efficient inference (ONNX/TFLite), Embedded ML, C/C++, Causal ML
Responsibilities
Research and prototype audio understanding models; Develop methods for sound event detection and anomaly detection; Build datasets and evaluation protocols; Integrate models into proof-of-concept systems with DSP engineers.
Seniority
Senior, hands-on IC
