Junior ML-AI Speech Enhancement and Denoising Software Engineer

Junior ML-AI Speech Enhancement and Denoising Software Engineer

ADI - Analog Devices

Leuven, Belgium

Summary and Responsibilities

We are looking for a passionate junior Speech Enhancement and Denoising Software Engineer to develop advanced deep learning models for next-generation audio and speech systems on hearables (earbuds, headphones, head mounted devices) and wearables. You will participate to the full lifecycle of hybrid DSP+ML based solutions — from research and prototyping to optimization and deployment on embedded hardware with customer support — while collaborating with cross-functional teams in AI, DSP, acoustics, hardware, and systems.

Preferred Qualifications

• ML for Audio: Strong academic records and project experience developing ML models for audio applications (e.g., speech enhancement, separation, or classification);
• Data Handling: Familiarity with audio dataset curation, augmentation strategies, and defining robust evaluation metrics;
• ML Systems: Basic understanding of ML pipelines (training, validation, deployment) emphasizing code reproducibility;
• Good knowledge of deep learning architectures (CNNs, RNNs, Transformers, diffusion models, generative approaches) applied to acoustic data;
• Proficiency in Python or Matlab and ML frameworks (PyTorch, TensorFlow);
• Edge Optimization: Project experience optimizing models (quantization, pruning) for resource-constrained embedded platforms;
• Product Concepts: Conceptual understanding of integration challenges in real-time systems (latency, power, robustness);
• Research Output: Evidence of research contributions through academic publications or innovative thesis work in audio ML or acoustics;
• Continuous Learning: Demonstrated enthusiasm for staying current with the latest research in audio ML.

Minimum Qualifications

• Advanced Degree: MSc or PhD in Computer Science, Electrical Engineering, Acoustics, Vibrations, Applied Math, or equivalent;
• 1+ years of relevant experience (including internship of academic projects);
• Experience developing and deploying ML models, specifically related to audio and speech;
• Track record of publications and/or patents if you have a PhD;
• Excellent communication and can-do mindset.