Senior Multimodal AI Scientist - Lip Sync & Animation

A pioneering AI company in the UK is seeking an applied scientist to scale and operationalize ADFA and lip sync work. This role focuses on developing and training models, automating quality evaluations, and collaborating with research teams. Ideal candidates should have a Master's or PhD, strong skills in Python and deep learning frameworks like PyTorch, and be proficient in 3D Computer Vision and Speech Synthesis. A hybrid work environment and competitive salary are offered.