Senior Research Engineer - Avatar AI Video Diffusion

Remote Worker LTD.; Greater London; Hybrid; GBP 90,000 - 150,000; Full time

Benefits offered by this job

Competitive compensation

Hybrid work with London office

25 days annual leave

Vibrant company culture

Referral program

Career growth opportunities

Job summary

Synthesia, the world’s leading AI video platform, is seeking a Senior Research Engineer to join the Interactive Avatars Team. You’ll work on diffusion models for avatar-centric video agents, shaping products used by thousands of businesses worldwide.

You’ll collaborate with researchers and engineers to turn ideas into real-world capabilities at scale. Ideal candidates have a strong ML/CV background, hands-on diffusion model experience, proficiency in PyTorch and Python, and a passion for robust,

Qualifications

• Strong ML and computer vision background with relevant industry experience.
• Hands-on experience with diffusion models (avatar-centric or video-focused).
• Proficient in PyTorch and familiar with modern ML frameworks and tooling.
• Strong Python engineering skills, clean research code, version control.

Responsibilities

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

Skills

Diffusion models

Computer vision

ML research

Python

Git

Tools

PyTorch

Python

Git

Job description

Synthesia, the world’s leading AI video platform, is seeking a Senior Research Engineer to join the Interactive Avatars Team. You’ll work on diffusion models for avatar-centric video agents, shaping products used by thousands of businesses worldwide.

You’ll collaborate with researchers and engineers to turn ideas into real-world capabilities at scale. Ideal candidates have a strong ML/CV background, hands-on diffusion model experience, proficiency in PyTorch and Python, and a passion for robust,