Research Assistant in Text-to-Music Models
SUTD
- Singapore
- Permanent
- Full-time
- Large-scale music feature extraction.
- Conduct advanced research in the development and enhancement of text-to-music models.
- Collaborate with interdisciplinary teams to integrate the latest diffusion and Large Language Model (LLM) technologies into the project.
- Leverage expertise in AI to advance the capabilities of text-to-music models.
- Explore innovative applications of music technology within the context of the project.
- Publish research findings in top-tier conferences and journals.
- Collaborate with graduate students on related projects.
- Bachelor or Master in Computer Science, Artificial Intelligence, Music Technology, or a related field.
- Strong background in AI, including experience with the latest diffusion, music generation, and LLM technologies.
- In-depth knowledge of music technology.
- Proven track record of research excellence as demonstrated by publications in reputable conferences and journals.
- Excellent programming skills and proficiency in programming languages (e.g., PyTorch).
- Ability to work independently and collaboratively in a team.
- Prior experience with the development of text-to-music models, or generative audio or music models is a bonus.
- Familiarity with music theory and MIR is a bonus.