Senior Applied Research Engineer - Video

📋 Description

• Develop and scale latent video diffusion models for human-centric video generation
• Design conditioning mechanisms for pose, emotion, scripts, and camera movement
• Lead end-to-end applied research and engineering projects to production impact
• Develop distributed training strategies (DDP, FSDP, DeepSpeed, sequence parallelism)
• Improve training stability in multi-GPU/multi-node environments under real compute constraints
• Design robust evaluation frameworks with automated metrics and human evaluation

🎯 Requirements

• Experience training deep learning models at scale (research or production)
• Strong Python programming and PyTorch experience
• Practical diffusion-model experience; image-generation required, video-generation preferred
• Proven large-scale multi-GPU/multi-node training experience
• Strong understanding of DDP, FSDP, DeepSpeed or similar
• Ability to run controlled experiments and make scientifically grounded decisions

🎁 Benefits

• Fully remote working environment within Europe
• Full-time employment
• Opportunity to build and work on production-scale video foundation models
• Influence next-generation human-centric video technology
• Work on scalability, model stability, controllability, evaluation, and inference optimization
• High-ownership environment with real-world product impact