Senior Applied Research Engineer - Video

📋 Description

• Develop and scale latent video diffusion models for human-centric video generation.
• Design conditioning to control pose, emotion, scripts, camera movement.
• Lead end-to-end R&D projects to production impact.
• Distributed training with DDP, FSDP, DeepSpeed, sequence parallelism.
• Improve training stability in multi-GPU/multi-node environments.
• Robust evaluation with automated metrics and human evaluation.

🎯 Requirements

• Strong experience training DL models at scale (research or production).
• Python and PyTorch proficiency.
• Experience with diffusion models; image-generation required, video preferred.
• Experience with large-scale multi-GPU/multi-node training.
• Knowledge of DDP, FSDP, DeepSpeed, or similar systems.
• Ability to design controlled experiments and analyze results scientifically.

🎁 Benefits

• Fully remote in Europe.
• Full-time employment.
• Opportunity to build on production-scale video foundation models.
• Influence next-gen human-centric video tech.
• Work on scalability, stability, controllability, evaluation, inference.
• High-ownership environment with real-world product impact.