Staff Research Engineer - Interactive Avatars

About the role

As a Staff Research Engineer you will join Synthesia’s Interactive Avatars team within the R&D department, tackling cutting‑edge challenges in generative AI and avatar‑centric video diffusion models. You will work on applied research that directly powers products used by thousands of businesses worldwide.

Key responsibilities

• Adapt diffusion models to incorporate diverse conditioning signals such as audio, motion, and interaction cues.
• Develop methods for streaming infinitely long video sequences at real‑time rates.
• 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 the data team to define data needs and ensure high‑quality datasets.

Required profile

• Strong background in machine learning, especially diffusion models, GANs, VAEs, and computer vision.
• Hands‑on experience with diffusion models for avatars or video, and familiarity with recent advances.
• Proficient in PyTorch and modern ML tooling, with solid Python engineering skills.
• Comfortable owning end‑to‑end model development, from data preparation to training and evaluation.

Required skills

• Python
• PyTorch
• Git / version control
• Diffusion models
• GANs
• VAEs
• Computer vision

What we offer

• Competitive compensation (salary, stock options, bonus).
• Hybrid work setting with offices in London, Amsterdam, Zurich, Munich or remote in Europe.
• 25 days of annual leave plus public holidays.
• Strong company culture with regular planning and social events.