PhD Research Intern - AI Music/Audio Generation

TL;DR

PhD Research Intern - AI Music/Audio Generation (Deep Learning): Designing and implementing novel deep learning algorithms for text-to-music and text-to-audio generation with an accent on state-of-the-art models, experimentation, and audio research. Focus on studying advanced literature, developing and evaluating models, analyzing results, and contributing to patents and academic publications.

Location: Onsite in the hirify.global Beijing office, China

Company

hirify.global Laboratories develops technologies for creating, delivering, and experiencing entertainment across audio, video, music, gaming, and immersive media.

What you will do

• Design and implement deep learning algorithms for music and audio generation projects, including text-to-music and text-to-audio systems.
• Collaborate with researchers across the full research cycle to advance state-of-the-art results.
• Read technical literature and develop creative research approaches.
• Design experiments, analyze results, and transfer learned knowledge into in-house deep learning models.
• Contribute to patent applications and academic paper writing.

Requirements

• Currently pursuing a PhD in deep learning for music and audio generation.
• Hands-on research experience in deep learning for music or audio generation.
• Experience with audio or multimodal language models, Transformers, diffusion models, or similar state-of-the-art approaches.
• Strong programming skills in Python and deep learning frameworks such as PyTorch.
• Excellent analytical and written communication skills.
• Good written communication skills in both Chinese and English are required.

Nice to have

• Publications in leading conferences or journals such as ICASSP, INTERSPEECH, NeurIPS, ICLR, or ICML.

Culture & Benefits

• Collegial culture with challenging research projects.
• Access to the resources of a global entertainment technology company.
• Flexible work approach and competitive compensation and benefits.
• Opportunity to contribute to technologies used across cinemas, smartphones, music, gaming, and other entertainment platforms.