Research Scientist II

Job description preview

From Adobe’s original posting

The Opportunity The Speech AI Lab at Adobe Research is seeking a Senior Audio Research Scientist to join our speech generative AI and multimodal research efforts, based in San Francisco. This role is ideal for researchers who stay deeply up to date with the latest AI model architectures and innovations and are motivated to push them forward in real-world creative systems. You will work alongside a world-class team of scientists and engineers to invent, evaluate, and scale next-generation audio and speech technologies—translating state-of-the-art research into products used by millions. Our lab values independent research leadership, technical excellence, and impact. We actively support publication at top venues, collaboration with academia, and rapid iteration from research insight to deployed technology. Responsibilities • Lead and execute independent research in speech generative AI, audio modeling, and multimodal learning (text and visuals), with a strong focus on modern large-scale model architectures. • Design, analyze, and advance state-of-the-art AI models and training procedures, including foundation models, representation learning, and generative systems for speech and…