ML Audio Engineer
Core
Design, train, and iterate on deep learning models for acoustic classification against noisy real-world audio, optimizing them for edge deployment.
Role type
ML Audio Engineer (Edge/Embedded)
Builds
Detection and classification models for audio, deployed on embedded hardware.
Domain
Audio signal processing, deep learning, edge computing.
Deliverable
production ML models
Required skills
deep learning, audio processing, microphone arrays, model deployment on constrained hardware, MLOps, data pipeline management
Preferred skills
beamforming, acoustic event detection, sound classification, DSP-heavy ML, field work with hardware
Technologies
deep learning frameworks, MLOps tools, embedded runtimes
Responsibilities
Design and train deep learning models for acoustic classification; optimize audio lineups for sound classification; build and maintain data pipelines including field recordings and augmentation; optimize models for edge deployment to meet latency and power budgets; manage MLOps stack including training infra and model monitoring
