Requirements
Technology stack:
- Pytorch (Python)
- Generative AI
- Generative speech enhancement
- Digital signal processing techniques for audio
- Tensorboard
- Jupyter Notebook
- Visual Studio Code
- Docker
Nice to have technologies:
- Diffusion modeling or similar modern generative AI techniques
- Notion
- Markdown
- VoIP technologies
- Speech codecs, including neural codecs
- PhD in speech AI or experience working as a speech AI researcher (preferred);
- working in agile methodologies (Scrum, Kanban);
- high communication skills;
- eager to learn and share knowledge;
- willing to work across multiple time zones and adjust work schedule accordingly;
- willing to travel if necessary (conferences, coworking events, etc.).