Dolby is looking to solve the problem of creating cutting edge multimodal technologies that drive next generation experiences, particularly in the area of developing AI solutions for Spatial Media/XR audio content creation workflow.
Requirements
- Solid knowledge of Audio, ML and AI fundamentals.
- High comfort level in creating Algorithms in Python
- Solid knowledge on audio signal analysis, spatial analysis, creation, and generation
- Solid knowledge on AI/ML, e.g. large language model and generative AI
- Familiarity with deep learning frameworks, e.g., TensorFlow, PyTorch, etc..
Responsibilities
- Develop AI models for spatial audio content creation and audio engineering workflow
- Develop multimodal foundation models for XR, with audio focus.
- Develop and combine deep learning methodologies with perceptually relevant signal processing and metrics.
- Partner with ATG researchers, develop solutions for the relevant applications.
Other
- PhD in Computer Science, Electrical and Computer Engineering, or similar fields
- Proven ability to pursue new areas of multimodal research for Audio, AI, and signal analysis, and demonstrate results through projects, prototypes, patent filings, and papers in peer reviewed journals and conferences
- Excellent problem-solving and partnership skills
- Excellent communication and presentation skills
- Respond aggressively to changing trends and new technologies and creates new algorithms to capitalize on them.
