Acoustics ML & DSP Engineer
Core
Develop, tune, and ship machine learning and DSP algorithms for voice audio front-end on Apple devices to ensure clear calls and reliable voice recognition.
Role type
Senior IC machine-learning and DSP engineer (acoustics/audio)
Builds
Voice processing features and algorithms for iOS, macOS, and wireless products
Domain
Consumer electronics, acoustics, and speech processing
Deliverable
production ML models
Required skills
Machine learning, digital signal processing, PyTorch, Python, real-time audio prototyping, causal streaming models, large-scale data pipelines, speech quality evaluation
Preferred skills
Audio DSP (echo/double-talk handling, beam-forming), hybrid signal processing and ML systems, telephony voice quality requirements, multi-modal machine learning, C/C++
Technologies
PyTorch, Python, Max/MSP, MATLAB, C/C++
Responsibilities
Develop new speech enhancement algorithms combining ML and DSP; tune and optimize algorithms for voice quality; debug issues by tracing to data, model, or signal chain; measure effects of front-end processing on telephony quality; follow state of the art in speech processing
Seniority
Senior, hands-on IC
