Senior Video AI Research Engineer — Production Diffusion

Synthesia; Greater London; On-site; GBP 120,000 - 180,000; Full time

Benefits offered by this job

Stock options

Remote/hybrid

25 days leave

Office in London

Job summary

Synthesia is the world’s leading AI video platform for business, enabling production-grade foundation models for human-centric video generation. You will join a fast-growing team exploring large-scale generative modeling, distributed systems, and production engineering to deliver high‑quality, scalable models used by tens of thousands of businesses.

This role emphasizes applied research with product impact, focusing on training recipes, distributed training, evaluation, and efficient inference

Qualifications

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

Responsibilities

• Develop latent video diffusion models tailored for human-centric video generation.
• Design conditioning mechanisms to improve control (pose, emotion, script, camera).
• 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 high engineering standards: reproducibility, experiment tracking, CI/CD, monitoring.

Skills

Deep learning

Python

PyTorch

Diffusion

Distributed training

Multi-GPU

Experiment design

Tools

CUDA

DeepSpeed

Docker

SLURM

Job description

Synthesia is the world’s leading AI video platform for business, enabling production-grade foundation models for human-centric video generation. You will join a fast-growing team exploring large-scale generative modeling, distributed systems, and production engineering to deliver high‑quality, scalable models used by tens of thousands of businesses.

This role emphasizes applied research with product impact, focusing on training recipes, distributed training, evaluation, and efficient inference