Senior Research Engineer – Interactive Avatars

Overview

As a Senior Research Engineer, you join Synthesia’s Interactive Avatars team to advance avatar-centric video diffusion models and bring research breakthroughs into product-ready capabilities. You’ll shape real-time, interactive video experiences used by thousands of businesses, collaborating across R&D to push the state of the art. This role blends rigorous experimentation with practical deployment to scale impactful AI video agents. You’ll thrive in a fast-moving, collaborative environment that values tangible impact and innovation.

Pay / Benefits

• Attractive compensation
• Hybrid work setting (London, Zurich, Munich)
• 25 days of annual leave + holidays
• Great culture with regular planning and socials
• Generous referral scheme
• Strong career growth opportunities

Responsibilities

• Adapt diffusion models to incorporate diverse conditioning signals (audio, motion, interaction cues)
• Develop methods for streaming infinitely long video sequences at real-time rates
• Work on the perceptual layer of interactive agents, including understanding user audio and generating contextual reactions
• Improve lip-sync accuracy, motion realism, and overall visual quality in video diffusion models
• Build robust evaluation frameworks and test suites for continuous quality tracking
• Collaborate with data team to define data needs and ensure high-quality datasets
• Stay updated with research in world models, interactive human/agent modeling, diffusion models and related areas

Key requirements

• Strong ML background with diffusion, GANs, VAEs and relevant industry experience
• Hands-on experience with diffusion models, ideally avatar-centric or video-focused
• Proficient in PyTorch and familiar with modern ML frameworks and tooling
• Strong Python engineering skills, confident with git and version control
• Outcome-driven, detail-oriented, and able to push state-of-the-art research into product impact
• Clear communicator of hypotheses, experiments, and results

• Strong communication
• Collaborative mindset
• Detail-oriented
• Diffusion models (avatar-centric or video-focused)
• PyTorch
• Modern ML frameworks and tooling

…