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 projects to production impact.
• Develop and optimize distributed training with DDP, FSDP, DeepSpeed, sequence parallelism.
• Improve training stability across multi-GPU and multi-node environments.
• Design evaluation frameworks with automated metrics and human review.

🎯 Requirements

• Experience training deep learning models at scale in research or production.
• Strong Python and PyTorch skills.
• Experience with diffusion models; video-generation preferred.
• Proven multi-GPU, multi-node training experience.
• Knowledge of distributed frameworks like DDP, FSDP, DeepSpeed.
• Ability to design controlled experiments and analyze results.

🎁 Benefits

• Fully remote working environment within Europe.
• Full-time employment.
• Opportunity to build production-scale video foundation models.
• Influence next-gen human-centric video tech.
• Work on scalability, stability, controllability and inference optimization.
• High-ownership environment driving toward real-world products.