Senior Applied Scientist - Multimodal/​Audio Driven Animation

About the Role

We are looking for a Senior Applied Scientist - Multimodal/Audio Driven Animation to join Flawless, the AI company that's revolutionizing Hollywood. This Senior Applied Scientist remote position is designed for a deeply technical, product-driven individual who will help scale and operationalize our ADFA and lip sync work. You will support and amplify ongoing research by owning model training pipelines, metrics, evaluation, and data workflows, ensuring our lip sync models improve reliably with every release.

What You'll Do

• Develop repeatable, scalable ADFA model training workflows across multiple datasets.
• Train, fine-tune, and manage lip sync model variants as trackers, data, and architectures evolve.
• Incorporate new datasets and model updates as they become available.
• Design, automate, and maintain ADFA metric testing pipelines.
• Generate new quantitative and qualitative metrics to evaluate lip sync quality.
• Produce comparisons, visualizations, and analyses to inform research and product decisions.
• Partner closely with ADFA researchers to support ongoing and future research initiatives.
• Collaborate with Science, Engineering, and Product teams to align research outputs with company goals.

Requirements

• MSc or PhD in a relevant field with industry experience in 3D Computer Vision, Speech Synthesis, or Computer Graphics.
• Proficiency in Python and deep learning frameworks (e.g., PyTorch).
• Strong foundation in computer science and problem-solving.
• High proficiency in math and statistical methods for signal processing.
• Experience with audio-visual learning, multimodal fusion, and 3D audio-driven face animation.
• Outstanding communication skills for collaboration with scientists and VFX artists.
• Experience with speech modeling and synthesis using deep neural networks.

Nice to Have

• Research experience with publications in major venues (e.g., CVPR, SIGGRAPH).
• Experience developing multi-modal systems integrating audio, text, and visual inputs.
• Experience with generative and cross-domain attention models for 3D visual speech synthesis applications.

What We Offer

• Autonomy in a hybrid working environment.
• Competitive salary and generous stock options.
• Opportunity to shape the future of a caring, creative, and collaborative company.
• Support for diverse perspectives and backgrounds.
• Flexible working hours and a focus on work-life balance.

Join us as a Senior Applied Scientist remote and be part of a team that is transforming the film industry with innovative AI solutions. If you are excited about this role and believe you can contribute meaningfully, we encourage you to apply!