Senior Applied Research Engineer - Video

📋 Description

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

🎯 Requirements

• Strong experience training deep learning models at scale in research or production.
• Strong Python and PyTorch skills.
• Practical experience with diffusion models; image-generation required, video-generation preferred.
• Experience with large-scale multi-GPU/multi-node training.
• Deep understanding of distributed training (DDP, FSDP, DeepSpeed or similar).
• Ability to design 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 generation tech.
• Work on challenging problems: scalability, stability, controllability, evaluation, inference
• High-ownership environment aiming at real-world products.