Senior Applied Research Engineer – Video Team

Synthesia is hiring a Senior Applied Research Engineer to join its Video team, working on production-grade foundation models for human-centric video generation. The role involves advancing latent video diffusion models, scaling distributed training, improving evaluation frameworks, and optimizing inference for real-world deployment. Ideal candidates have strong PyTorch and distributed training experience, with hands-on diffusion model expertise.

• Develop and scale latent video diffusion models for human-centric video generation.
• Design conditioning mechanisms for pose, emotion, script, and camera control.
• Advance distributed training strategies (DDP, FSDP, DeepSpeed, sequence parallelism) under real compute constraints.
• Improve training stability at multi-node scale.
• Design rigorous evaluation frameworks combining automated metrics and structured human evaluation.
• Optimize inference for low latency, high resolution, and cost efficiency.
• Run controlled ablations and experiments to drive high-signal modeling decisions.
• Contribute to engineering standards: reproducibility, experiment tracking, CI/CD, monitoring.

• Strong experience training deep learning models at scale.
• Strong Python and PyTorch skills.
• Hands-on experience with diffusion models (image domain required; video preferred).