Senior Applied Scientist - Multimodal/Audio Driven Animation

Develop and operationalize audio-driven face animation and lip sync models.

• •Flawless is looking for a Senior Applied Scientist to scale and operationalize audio-driven face animation (ADFA) and lip sync models.
• •You will bridge the gap between research and production, ensuring model improvements are validated and shipped reliably.
• •Key Responsibilities Develop scalable ADFA model training workflows and manage lip sync model variants.
• •Design and automate metric testing pipelines to evaluate lip sync quality.
• •Collaborate with researchers, engineers, and VFX artists to align outputs with product goals.
• •Requirements MSc or PhD in Computer Vision, Speech Synthesis, or Computer Graphics with industry experience.
• •Proficiency in Python and expertise with PyTorch and OpenCV.
• •Strong background in signal processing, math, and statistical methods.