Senior Research Engineer - Interactive Avatars

Skills

About the Role

You will adapt and improve avatar-centric video diffusion models using audio, motion, and interaction cues. You will develop real-time streaming methods, improve lip-sync and motion realism, build evaluation frameworks, define data needs, and translate research advances into product capabilities.

Requirements

• Industry experience in machine learning and computer vision
• Hands-on experience with diffusion models
• Proficiency in PyTorch and modern machine learning frameworks and tooling
• Strong Python engineering skills
• Git and version-control knowledge
• Ability to communicate hypotheses, experiments, and results clearly

Responsibilities

• Adapt diffusion models to incorporate audio, motion, and interaction cues
• Develop methods for streaming infinitely long video sequences at real-time rates
• Develop the perceptual layer for understanding user audio and generating contextual reactions
• Improve lip-sync accuracy, motion realism, and visual quality in video diffusion models
• Build evaluation frameworks and test suites for continuous quality tracking
• Collaborate with the data team to define data needs and ensure dataset quality
• Stay current with research in world models, interactive human and agent modeling, and diffusion models

Benefits

• Hybrid work setting with offices in London, Zurich, and Munich
• 25 days of annual leave plus public holidays
• Regular planning and social events at company hubs
• Generous referral scheme