PhD Research Intern - Music-Conditioned Video (AI)

Location: Beijing, China; position based in the hirify.global Beijing office

Company

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

What you will do

• Design and implement deep learning algorithms for music-conditioned video generation, including text-to-video and audio-to-video applications.
• Collaborate with researchers across the full research cycle to advance state-of-the-art results.
• Read research literature and develop creative solutions for music and video generation.
• 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 video generation.
• Hands-on research experience in deep learning for music or video generation, such as text-to-video or audio-to-video.
• Experience with state-of-the-art models, including audio or multimodal language models, Transformers, or diffusion models.
• Strong programming skills in Python and experience with deep learning tools such as PyTorch.
• Strong analytical skills and the ability to communicate complex information efficiently.
• Good written communication skills in both Chinese and English.

Nice to have

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

Culture & Benefits

• Collegial culture and challenging research projects.
• Access to resources within hirify.global's Advanced Technology Group.
• Flexible work approach and compensation and benefits package.