Senior Video Diffusion Research Engineer

Neura Market; United Kingdom; Remote; EUR 90,000 - 140,000; Full time

Benefits offered by this job

Competitive compensation (salary + 100

Fully remote from Europe or hybrid (UK

25 days annual leave + holidays

Office presence in London, Amsterdam,

Stock options and bonus

Job summary

Synthesia is seeking a Research Engineer to help build production-grade foundation models for human-centric video generation. You’ll work at the intersection of large-scale generative modeling, distributed systems, and production engineering, delivering real-world impact for tens of thousands of businesses.

You’ll own end-to-end research projects, advance training recipes, scale distributed systems, improve evaluation, and optimize inference for efficiency.

Qualifications

• Strong experience training deep learning models at scale.
• Hands-on Python and PyTorch expertise.
• Experience with diffusion models (image domain required; video preferred).
• Experience with large scale multi-GPU / multi-node training.
• Knowledge of distributed training (DDP, FSDP, DeepSpeed or similar).
• Ability to design controlled experiments and interpret noisy results.

Responsibilities

• Own and execute end-to-end research and engineering projects from hypothesis to production impact.
• Develop and scale latent video diffusion models for human-centric video generation.
• Design conditioning mechanisms for improved control (pose, emotion, script, camera).
• Advance distributed training strategies under real compute constraints.
• Improve training stability at multi-node scale.
• Design rigorous evaluation frameworks combining automated metrics and human evaluation.
• Optimize inference for low latency, high resolution, and cost efficiency.
• Maintain reproducibility, experiment tracking, CI/CD, and monitoring.

Skills

Deep learning at scale

Python

PyTorch

Diffusion models

Multi-GPU / multi-node

Distributed training (DDP / FSDP / DS)

Experimental design

Job description

Synthesia is seeking a Research Engineer to help build production-grade foundation models for human-centric video generation. You’ll work at the intersection of large-scale generative modeling, distributed systems, and production engineering, delivering real-world impact for tens of thousands of businesses.

You’ll own end-to-end research projects, advance training recipes, scale distributed systems, improve evaluation, and optimize inference for efficiency.