Audio Deep Learning Engineer

femtoAI is a technology company focused on innovative audio solutions, and they are seeking a Deep Learning Engineer to design and develop audio algorithms. The role involves optimizing deep learning models for audio processing and collaborating with customers to deliver tailored solutions.

Responsibilities:

• Design, develop, and deploy deep-learning-based and classical DSP audio algorithms for our SPU platform
• Leverage innovative model compression techniques to optimize performance-per-joule on custom silicon
• Be a core contributor to our deep learning and DSP development platform, advancing novel algorithms for audio processing
• Collaborate directly with customers across diverse industries to deliver impactful solutions and exciting new features
• Develop and optimize deep learning models for audio processing, including tasks like speech enhancement, beamforming, event detection, sound localization, voice identification, voice interfaces, noise reduction, echo cancellation, feedback cancellation, and more
• Drive innovation in model efficiency, compression, and deployment on embedded platforms
• Leverage multi-sensor data to improve algorithm performance in difficult environments
• Work closely with customers to understand their needs and tailor solutions to meet their goals
• Contribute to the end-to-end process of model development, from research and prototyping to deployment on hardware