Senior Applied Research Engineer - Video
Recruiter Fit Breakdown & Candid Summary
Synthesia is seeking a Senior Applied Research Engineer to join their Video team and develop production-grade foundation models.
This role bridges cutting-edge generative AI research with real-world product deployment, focusing on video diffusion models and distributed training at scale.
The ideal candidate is an outcome-focused deep learning practitioner with robust PyTorch and distributed training experience who prioritizes shipping over pure theory.
Those looking for purely academic research or lacking large-scale multi-GPU training experience should not apply.
Role Responsibilities
- 1Develop and scale latent video diffusion models tailored for human-centric video generation
- 2Design conditioning mechanisms to improve control over pose, emotion, script, and camera without sacrificing fidelity
- 3Advance distributed training strategies like DDP, FSDP, DeepSpeed, and sequence parallelism under real compute constraints
- 4Design rigorous evaluation frameworks combining automated metrics and structured human evaluation
- 5Optimize inference for low latency, high resolution, and cost efficiency
- 6Run controlled ablations and experiments to drive high-signal modeling decisions
Skills Matrix
Must-Have Skills
Nice-to-Have Skills
Will an ATS filter reject your resume for this role?
Check your keyword match score, missing must-have skills, and formatting flags — before you apply.
No signups. Free check in 3 seconds.
Ready to submit your application?
Apply directly on Synthesia's official job portal.