Senior ML/AI Audio and Acoustics SW Engineer

About Analog Devices

Analog Devices, Inc. (NASDAQ: ADI ) is a global semiconductor leader that bridges the physical and digital worlds to enable breakthroughs at the Intelligent Edge. ADI combines analog, digital, and software technologies into solutions that help drive advancements in digitized factories, mobility, and digital healthcare, combat climate change, and reliably connect humans and the world. With revenue of more than $9 billion in FY24 and approximately 24,000 people globally, ADI ensures today's innovators stay Ahead of What's Possible. Learn more at  and on LinkedIn and Twitter (X).

ML/AI Audio and Acoustics Software Engineer

Location

Belgium (Hybrid / Onsite)

Summary

We are looking for an experienced ML/AI Audio & Acoustics Engineer to contribute to the design and implementation of state-of-the-art deep learning models for very low latency audio and speech enhancement applications in ANC hearables. You will join a multidisciplinary team of ML scientists, acoustics engineers, and DSP software developers, working on technologies that improve audio capture, hearing enhancement, and rendering in real-world devices.

Responsibilities

• Assist in developing, training, and evaluating deep learning models for tasks such as speech enhancement, noise suppression, source separation, dereverberation, and classification.

• Contribute to data collection, dataset curation, pre-processing, and augmentation pipelines.

• Prototype models in Python (PyTorch / TensorFlow), validate performance against acoustic datasets, and iterate with senior engineers.

• Support model optimization for inference (quantization, pruning, compression) on embedded / mobile platforms.

• Collaborate with acoustics engineers to understand physical constraints and integrate ML solutions with microphones, speakers, and arrays.

• Contribute to lab measurements, test automation, and benchmarking of algorithms in controlled and real-world environments.

• Document design choices, results, and learnings.

Minimum Qualifications

• Master's degree in Computer Science, Electrical Engineering, Acoustics, Applied Math, or equivalent.

• Strong knowledge of deep learning and neural network architectures (CNNs, RNNs, Transformers) with application to audio/speech/hearing.

• Good knowledge of speech enhancement and adaptive filtering DSP techniques.

• Good knowledge and understanding about ANC.

• Proficiency in Python and ML frameworks (PyTorch, TensorFlow, Keras).

• Basic knowledge of audio signal representation (STFT, mel spectrograms, waveforms).

• Familiarity with both Windows and Linux development environments and version control (Git).

• Strong problem-solving and willingness to learn in a multidisciplinary environment.

• Start-up mindset.

Preferred Qualifications

• Internship or thesis experience in audio ML (speech enhancement, separation, or classification).

• Exposure to on-device ML (TinyML, edge inference, quantization).

• Experience with data labeling, augmentation, or large-scale training pipelines.

• Basic C/C++ skills for model integration.

#LI-BM1

For positions requiring access to technical data, Analog Devices, Inc. may have to obtain export  licensing approval from the U.S. Department of Commerce - Bureau of Industry and Security and/or the U.S. Department of State - Directorate of Defense Trade Controls.  As such, applicants for this position – except US Citizens, US Permanent Residents, and protected individuals as defined by 8 U.S.C. 1324b(a)(3) – may have to go through an export licensing review process.

Analog Devices is an equal opportunity employer. We foster a culture where everyone has an opportunity to succeed regardless of their race, color, religion, age, ancestry, national origin, social or ethnic origin, sex, sexual orientation, gender, gender identity, gender expression, marital status, pregnancy, parental status, disability, medical condition, genetic information, military or veteran status, union membership, and political affiliation, or any other legally protected group.