Computer Vision Engineer – Synthetic Media
Location: London, UK (Hybrid – Multiple Global Offices)
Company: Series B AI Video Generation Platform
Shape the future of content creation as synthetic media revolutionizes how the world produces video content. With $336M+ raised and trusted by 70% of Fortune 100 companies, we’re the world’s leading AI video creation platform, serving over 1 million users globally. Our breakthrough technology replaces traditional cameras and complex video editing with AI-powered synthesis, enabling anyone to create high-quality videos with simple text inputs. As traditional video production faces sustainability challenges and rising costs, our AI-generated videos deliver 215,712 metric tons less CO2 emissions compared to conventional filming methods.
What You’ll Do:
- Develop state-of-the-art neural rendering techniques for photorealistic human synthesis
- Build 3D neural representations for controllable video generation of people
- Create efficient models for real-time facial expression and gesture synthesis
- Research novel approaches for text-to-video generation and avatar customization
- Optimize inference pipelines for scalable video synthesis at enterprise scale
Requirements:
- MSc/PhD in Computer Vision, Computer Graphics, or Machine Learning
- 4+ years experience with 3D reconstruction, neural rendering, or generative models
- Expertise in GANs, diffusion models, NeRFs, or related generative technologies
- Strong programming skills in Python, PyTorch, and CUDA
- Experience with facial analysis, human pose estimation, or 3D modeling
What We Offer:
- £70k-£120k + equity in a rapidly scaling AI media company
- Work on cutting-edge research in synthetic media and neural rendering
- Collaborate with world-renowned researchers from UCL, Stanford, and TUM
- Flexible work arrangement across London, NYC, Copenhagen, and other offices
