Research Scientist, GenAI - Multimodal Audio (Speech, Sound and M...
META - Bellevue, Washington, us, 98009Work at META
Overview
- Apply
Overview
Research Scientist, GenAI - Multimodal Audio (Speech, Sound and Music) Responsibilities
Full life-cycle research on multimodal generative foundation models with a focus on the audio modality, including bringing up ideasDesigning and implementing models and algorithmsCollecting and selecting training data, training / tuning / scaling the models, evaluating the performance, open sourcing and publicationWork together with collaborating teams (e.g. language and vision) to leverage each other and deliver the high-level goals.Minimum Qualifications
Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience.Solid track record of research in the audio (speech, sound, or music) or vision (image or video) domains. Can be publication records or unpublished industrial experience.PhD degree in the related field with 3+ years of experience, or BS degree with 5+ years of industrial research experience in the related field.Related research fields: audio (speech, sound, or music) generation, text-to-speech (TTS) synthesis, text-to-music generation, text-to-sound generation, speech recognition, speech / audio representation learning, vision perception, image / video generation, video-to-audio generation, audio-visual learning, audio language models, lip sync, lip movement generation / correction, lip reading, etc.Proven knowledge in neural networks.Experienced in one of the following popular ML frameworks: Pytorch, Tensorflow, JAX.Experienced in Python programming language.Solid communication skills.Preferred Qualifications
Solid publication track record in related fields.Solid experience in either of the following: audio dataset curation, model scaling, audio generation model evaluation.Experienced in large-scale data processing.Experienced in solving complex problems involving trade-offs, alternative solutions, cross functional collaboration, taking into account diverse points of views.