Staff Research Engineer — Interactive Avatar Diffusion

SLAMcore; United Kingdom; Hybrid; GBP 120,000 - 180,000; Full time

Benefits offered by this job

Stock options

Hybrid work

Office in London

Job summary

Synthesia is the world’s leading AI video platform and is seeking a Staff Research Engineer to join our R&D team in London. You’ll work on avatar-centric interactive video diffusion models, with responsibilities spanning data-driven model development, real-time streaming, and quality assessment.

You will collaborate with a 40+ researcher/engineer team, focus on lip-sync, motion realism, and datasets, and contribute to world-model research while delivering practical, production-ready results.

Qualifications

• Strong ML and computer vision background with relevant industry experience.
• Hands-on experience with diffusion models, ideally avatar-centric or video-focused.
• Proficient in PyTorch and familiar with modern ML tooling.
• Clear communicator of hypotheses, experiments, and results.

Responsibilities

• Adapt diffusion models to incorporate diverse conditioning signals (e.g., 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 appropriate contextual reactions.
• Improve lip-sync accuracy, motion realism, and overall visual quality in video diffusion models.
• Build robust evaluation frameworks and test suites to enable continuous quality tracking.
• Collaborate closely with our data team to define data needs and ensure high-quality datasets.
• Stay up to date with research in world models, interactive human/agent modeling, diffusion models, and related areas.

Skills

Diffusion models

PyTorch

Python

Computer vision

Research & development

Experiment design

Git / version control

Tools

Git

ML frameworks

Job description

Synthesia is the world’s leading AI video platform and is seeking a Staff Research Engineer to join our R&D team in London. You’ll work on avatar-centric interactive video diffusion models, with responsibilities spanning data-driven model development, real-time streaming, and quality assessment.

You will collaborate with a 40+ researcher/engineer team, focus on lip-sync, motion realism, and datasets, and contribute to world-model research while delivering practical, production-ready results.