Applied Research Engineer (Video Generative AI)

Location: Remote in Europe

Company

Synthesia develops an AI video platform for business and enterprise skill development, with products powered by in-house generative AI research and engineering.

What you will do

• Develop and scale latent video diffusion models for human-centric video generation.
• Design conditioning mechanisms for pose, emotion, script, and camera control while preserving fidelity.
• Advance distributed training strategies using DDP, FSDP, DeepSpeed, and sequence parallelism, and improve multi-node training stability.
• Design evaluation frameworks combining automated metrics with structured human evaluation, and run controlled ablations.
• Optimize inference for low latency, high resolution, and cost efficiency.
• Maintain high engineering standards through reproducibility, experiment tracking, CI/CD, and monitoring.

Requirements

• Strong experience training deep learning models at scale.
• Strong Python and PyTorch skills, with experience using CUDA.
• Hands-on experience with diffusion models; image-domain experience is required and video experience is preferred.
• Experience with large-scale multi-GPU and multi-node training, including DDP, FSDP, DeepSpeed, or similar distributed training systems.
• Ability to design controlled experiments and interpret noisy results.
• Experience with video diffusion models and avatar or human-centric generation.
• Experience optimizing inference systems for production.
• Experience or familiarity with DeepSpeed, distributed inference, sequence parallelism, AWS, SLURM, Docker, GitHub, and CI/CD pipelines.
• Research-driven and outcome-focused approach, with the ability to explore multiple ideas quickly and discontinue low-signal directions.
• Clear scientific communication, independent execution, and active cross-team collaboration.

Nice to have

• Familiarity with world or interactive models.
• Experience with GANs or VAEs.

Culture & Benefits

• Remote work from Europe.
• High-ownership environment focused on building and shipping production systems.
• Work on human-centric video generation with real-world product impact.
• Focus on AI safety, ethics, security, and people-first technology.
• Technical collaboration with AI researchers and engineers across Europe and the US.