Acoustics ML & DSP Engineer

Apple • Boulder, CO

1d

About The Position

The Audio System Tuning team is seeking an Acoustics ML and DSP Engineer to develop, tune, and ship machine-learning and digital signal-processing algorithms for voice audio front ends across iOS, macOS, and wireless products. This applied, product-focused role aims to improve the clarity and naturalness of phone and video calls and the reliability of Siri and voice recognition in real-world conditions. The engineer will take algorithms from prototype through on-device testing and into production on Apple devices used by millions of customers.

The role involves developing speech-enhancement algorithms that combine machine learning and DSP; using and extending large-scale data preprocessing, simulation, and cloud training pipelines; and creating new pipelines when needed. The engineer will tune, optimize, and listen to algorithms, and debug issues by tracing them to data, models, or the signal chain. Work will address voice quality and intelligibility in challenging conditions such as echo, double talk, and noise, and measure the impact of front-end processing on telephony quality and machine-listening applications. The engineer will track developments in speech processing and related fields and collaborate with tuning, DSP, and audio ML colleagues, as well as hardware and software partners.

Requirements

• MS with at least 3 years of relevant experience, or a PhD, in Acoustics, Audio, Electrical Engineering, Computer Science, or a related field.
• Solid grasp of acoustics and signal-processing fundamentals.
• Experience shipping audio or speech-enhancement machine-learning algorithms from prototype to production.
• Proficiency with PyTorch and Python, including version control, testing, and reproducible experiments.
• Working knowledge of Max/MSP for real-time audio prototyping.
• Experience with causal, streaming models subject to real-time latency and compute constraints.
• Experience using large-scale data and cloud training pipelines, including preprocessing and data simulation, and building such pipelines when needed.
• Working knowledge of speech-quality evaluation, including objective metrics, telephony-quality and echo-performance measures, and subjective listening tests.
• Understanding of the state of the art in speech processing and adjacent fields.
• Ability to explore and test ideas, prioritize, and deliver across several projects in a fast-paced environment.
• Strong written and verbal communication skills and ability to work in cross-functional teams.

Nice To Haves

• Experience with audio DSP, such as echo and double-talk handling, microphone-array processing, beam-forming, dynamics processing, equalization, and noise suppression.
• Experience with hybrid systems combining classical signal processing and machine learning.
• Familiarity with telephony voice-quality requirements.
• Knowledge of front-end processing for speech recognition and machine listening.
• Experience with multimodal machine learning.
• Strong coding and debugging skills in Python and C/C++, plus MATLAB for analysis.
• Knowledge of transducers and their acoustic integration.
• Curiosity and eagerness to try new ideas quickly while keeping multiple product programs on track.

Responsibilities

• Develop speech-enhancement algorithms combining machine learning and DSP, and take them from prototype to production on Apple devices.
• Use and extend large-scale data preprocessing, simulation, and cloud training pipelines; build new pipelines where needed.
• Tune, optimize, and listen to algorithms, and debug issues by tracing them to data, models, or the signal chain.
• Improve voice quality and intelligibility for telephony and voice calls under challenging conditions, including echo, double talk, and noisy environments.
• Measure the effect of front-end processing on telephony quality and machine-listening applications.
• Follow the state of the art in speech processing and adjacent fields.
• Work cross-functionally with tuning, DSP, and audio ML colleagues and partners across hardware and software organizations.
• Balance and deliver work across several projects in a fast-paced environment.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level