Audio Algorithm Engineer (AI)

TL;DR

Audio Algorithm Engineer (AI): Designing and implementing real-time speech enhancement algorithms for wearable devices with an accent on noise reduction, dereverberation, and echo cancellation. Focus on training deep learning models and optimizing algorithms for low-latency embedded deployment.

Location: Sophia-Antipolis (Valbonne), France

Company

hirify.global is a global leader in secure connectivity solutions for embedded applications, specializing in low-power AI and DSP technologies for the wearable market.

What you will do

• Design and implement advanced signal processing algorithms for speech enhancement in real-world acoustic environments.
• Develop Proof of Concepts to demonstrate algorithm performance.
• Design and train deep learning models for speech denoising, dereverberation, and source separation.
• Optimize algorithms for low-latency and embedded systems deployment.
• Conduct benchmarks and evaluate performance using speech quality metrics and listening tests.
• Collaborate with software engineers to integrate solutions into voice products.

Requirements

• Master’s degree or PhD in computer science engineering with a specialization in signal processing and machine learning.
• 1-2 years of experience in audio research and development.
• Strong background in digital signal processing and speech processing fundamentals.
• Proficiency in Python, Matlab, and C.
• Experience with machine learning frameworks such as PyTorch.
• Knowledge of real-time processing constraints and neural networks for speech enhancement.

Nice to have

• Publications in speech and audio processing.
• Experience with voice communication systems such as mobile phones, smart speakers, or hearing aids.