Staff Research Engineer - Generative Video
Is this job for you?
Build my CV Build your CV and see how well you match this role — and every other one.
Track your applications on mobile The free Whileresume app, on iPhone and Android.
The role
As a Staff Research Engineer, you will bridge research and production to deliver scalable generative video systems.
Translate cutting-edge ideas (diffusion-based video generation, multimodal conditioning, temporal consistency) into robust, production-ready implementations.
Set technical direction for projects across text-to-video, image-to-video, video-to-video, and video editing, balancing quality, latency, cost, and safety.
Design and build end-to-end training and inference pipelines, evolving prototypes into robust systems with benchmarking, monitoring, regression testing, and guardrails.
Drive rigorous experiments to improve temporal coherence, identity preservation, prompt adherence, and runtime performance.
Mentor teammates, lead design and code reviews, and elevate engineering standards through strong observability and operational practices.
Translate cutting-edge ideas (diffusion-based video generation, multimodal conditioning, temporal consistency) into robust, production-ready implementations.
Set technical direction for projects across text-to-video, image-to-video, video-to-video, and video editing, balancing quality, latency, cost, and safety.
Design and build end-to-end training and inference pipelines, evolving prototypes into robust systems with benchmarking, monitoring, regression testing, and guardrails.
Drive rigorous experiments to improve temporal coherence, identity preservation, prompt adherence, and runtime performance.
Mentor teammates, lead design and code reviews, and elevate engineering standards through strong observability and operational practices.
See the full job post
Responsibilities, requirements, skills and benefits — create your free account.
or
Already have an account?
Log inYou might also like these jobs
No closely matching jobs yet — here are the most recent ones.