Description
Dolby is hiring a Senior Multimodal AI Researcher, Audio to join its Machine Reasoning and Perception team and advance multimodal AI for audio, speech, and music applications. The role focuses on generative modeling, multimodal representations, self- and semi-supervised learning, and technologies such as diffusion, autoregressive, masked generative transformer, and language-model-based audio systems. Responsibilities include developing prototypes and demonstrations, transferring technology to product groups, publishing research, mentoring interns, and advising on deep-learning advancements. The position requires a Ph.D. in Computer Science or a similar field, strong deep-learning and audio knowledge, Python and deep-learning-framework expertise, and a strong publication record.
