AI PhD Intern, Sound Experiences Lab

As an intern, you will join the Research team to develop innovative AI solutions for spatial audio processing. Enrolled in a PhD program on subjects related to audio processing and AI for the entire duration of the internship. Demonstrable experience in signal processing applied to audio. Demonstrable experience in AI applied to audio, with hands-on experience in at least one deep learning framework in Python. Solid mathematical background. Experience in research, reflected in research publications. Python programming skills and experience with data preparation and processing. Good communication skills The candidate is expected to work at least part of the time on-site, in the Barcelona office. Design, implement and train advanced deep learning models for spatial audio processing tasks, leveraging the latest AI techniques, including self-supervised learning, few-shot learning, and multi-modal learning. Prepare and curate high-quality datasets using data augmentation, synthetic data generation, and self-supervised learning techniques. Collaborate with the research group in Barcelona on related tasks. Present research findings and contribute to patent applications and scientific publications.