Applied Scientist at leading AI film-tech studio revolutionizing global storytelling

You will bridge the gap between research and production by operationalizing end-to-end multimodal pipelines for state-of-the-art lip sync and audio/video generation. By owning model training, dataset curation, and automated evaluation metrics, you will ensure that cutting-edge research reliably scales into production systems that redefine the future of global cinema and VFX.

• Develop and scale repeatable audio/video dataset curation pipelines and training workflows for advanced lip sync and multimodal models.
• Design and automate quantitative metrics and qualitative evaluation pipelines to provide rigorous validation of model improvements and performance.
• Partner with cross-functional research and engineering teams to integrate optimized model variants into high-performance production environments.

• Holds an MSc or PhD in a related field with deep expertise in PyTorch, OpenCV, and signal processing for audio-visual learning.
• Possesses extensive experience in speech synthesis, 3D computer vision, or multimodal fusion, specifically working with audio-driven face animation.
• Demonstrates a strong product mindset, with the technical proficiency to navigate both complex algorithmic design and large-scale data engineering tasks.

===

• Work at the bleeding edge of AI for the film industry, building systems that enable seamless, high-fidelity actor performances across multiple languages.
• Join a world-class team of scientists and engineers where your work directly impacts the quality of major motion picture productions and global content distribution.
• Influence the entire lifecycle of generative models, moving beyond theoretical research to build robust, automated systems that ship to users at scale.