Responsibilities
Research and development in one (or more) of the projects below:
- AI music composition. To generate functional music for jogging, sleeping, driving, reading, etc.
- Content-based hit song prediction and music recommendation,
- High level music understanding, such as music emotion, music perception, performance style and singing skill analysis.
- Multimodal music generation and pairing with video, picture and lyrics.
The successful applicant will lead a team of music & audio engineers to carry out cutting edge research, direct collaborative research project with university, and collaborate with other Huawei research and product teams overall the world.
Professional Knowledge
- Music codec for LLM. To develop a next generation music codec which is LLM friendly. Able to capture expressive music characteristics in a relatively lower bit rate.
- AI Music generation. Generate music for a given text description, lyrics, and/or singing voice in an E2E manner.
- AI Digital audio workstation. Develop foundation MIR technology, and advanced functions such as editable music accompaniment generation for a given singing voice or instrumental performance, music continuation, and AI mixing/remastering.
- The selected candidate will lead a small team of engineers and lead a university technical collaboration project. The technical outcome will be deployed in more than 1 billion HarmonyOS devices such as smartphones, tablet and cars.
Service Skill
- PhD in computer science, audio engineering or related field, with strong publication record demonstrating innovative research.
- Strong understanding in the latest AI technology, familiar with such as Transformer, Diffusion, LORA. Strong experience in LLM training, fine-tuning and RAG.
- Proficient in python or C++, deep understanding in common algorithms and data structures, familiar with PyTorch or any machine learning framework.
- The Job rank (Senior / Principal ) depends on candidate’s qualification and experience.
Optional Qualification
- Experienced in pop music production and music performance. Familiar with at least one DAW.
- Experienced in traditional audio DSP technique.