Senior Applied Research Engineer - Video Team
SynthesiaAlso available on
Job Description
📋 Description Own and execute end-to-end research and production-impact projects. Develop latent video diffusion models for human-centric video generation. Design conditioning for pose, emotion, script, and camera. Advance distributed training strategies under real compute constraints. Improve training stability at multi-node scale. Optimize inference for low latency, high resolution, and cost efficiency. 🎯 Requirements Must-have: Deep learning at scale; Python & PyTorch. Must-have: Diffusion models; multi-GPU/multi-node training. Must-have: Distributed training (DDP/FSDP/DeepSpeed) and experimental design. Nice-to-have: Video diffusion models. Nice-to-have: Avatar/human-centric generation. Nice-to-have: Inference optimization for production. 🎁 Benefits Competitive compensation (salary + stock options + bonus) Fully remote from Europe or hybrid with offices in London, Amsterdam, Zurich, Munich 25 days leave + public holidays Great culture with planning and hub socials Other location benefits