Research Scientist Intern, Multimodal LLM and Speech-to-Speech Translation (PhD)

Job description

The Meta Reality Labs Research team brings together researchers, developers, and engineers to build the future of augmented and virtual reality. Our research spans the technologies that enable next-generation AR glasses and VR headsets, with the goal of transforming how people interact with their surroundings and connect with one another. The Reality Labs Research audio team develops technologies that redefine human hearing and communication. We seek to help people understand the world around them, communicate in challenging listening environments, and connect across languages. Learn more about our research here. We are seeking Research Scientist Interns to advance multimodal large language models (MLLMs) and speech-to-speech translation (S2ST) for next-generation wearable and AR/VR experiences. Research opportunities include models that integrate audio, speech, vision, and language for multimodal understanding and reasoning; conversational speech models; and streaming speech translation that preserves meaning, speaker characteristics, and expressive prosody. Interns will investigate research questions in one or more of these areas, develop and evaluate novel models, and collaborate with researchers and engineers to demonstrate their potential in real-world applications. Our internships are twelve (12) to twenty-four (24) weeks long, with various start dates throughout the year.