Senior Applied Research Engineer - Video
Synthesia · Remote · Europe ·
COMPENSATION
€•• – ••k
Listed on the employer's job board (Ashby)
- Senior level role
- Fully remote / Hybrid
- Python + PyTorch
- Video diffusion models
- Distributed training
Join the Video team at Synthesia to develop and optimize video base models that power realistic, controllable synthetic humans. You will work at the intersection of research and engineering, focusing on scaling training recipes, improving evaluation frameworks, and optimizing inference for real-world deployment.
What you'll do
- Develop and scale latent video diffusion models for human-centric generation
- Design conditioning mechanisms to improve control over pose, emotion, and camera
- Advance distributed training strategies using DDP, FSDP, and DeepSpeed
- Improve training stability across multi-node scale environments
- Design rigorous evaluation frameworks combining automated metrics and human feedback
- Optimize inference pipelines for low latency, high resolution, and cost efficiency
- Run controlled ablations and experiments to drive modeling decisions
- Maintain high engineering standards including reproducibility and CI/CD
What you'll need
- Strong experience training deep learning models at scale
- Proficient in Python and PyTorch
- Hands-on experience with diffusion models in the image domain
- Experience with large-scale multi-GPU and multi-node training
- Good understanding of distributed training frameworks like DeepSpeed or FSDP
- Ability to design controlled experiments and interpret noisy results
Nice to have
- Experience with video diffusion models
- Background in avatar or human-centric generation
- Familiarity with world or interactive models
- Experience with GANs or VAEs
- Experience optimizing inference systems for production
Stack
- Python
- PyTorch
- CUDA
- DeepSpeed
- AWS
- SLURM
- Docker
- GitHub
How you'll work
- Headquartered in London with teams in Europe and the US
- Remote-friendly culture with offices available
- Fast-paced environment focused on shipping outcomes
What you get
- Work on production-scale video foundation models
- High-ownership environment with technical autonomy
- Backed by premier investors including Accel and Nvidia