Applied Scientist, Prime Video - Generative AI (Video)
Core
Research and develop generative models for controllable synthesis across images, video, vector graphics, and multimedia to enhance Prime Video's content localization, image/video understanding, and personalization.
Role type
Applied Scientist (Generative AI & Computer Vision)
Builds
Production-ready generative AI systems for content creation, pre-visualization, compositing, and post-production pipelines at Amazon scale.
Domain
Entertainment, Generative AI, Computer Vision, Multimedia
Deliverable
production ML models
Required skills
Generative models (diffusion, flow, transformers), Image/video synthesis and editing, PyTorch, Modern DL toolkits (Hugging Face), Java/C++/Python programming, Model building for business applications
Preferred skills
Controllable generation methods (LoRA, ControlNet, parameter-efficient tuning), Visual-language modeling, Agentic pipelines, Harmonization, Relighting, Style transfer, Lip-sync, Segmentation, Matting, Depth estimation, 3D camera/scene modeling
Technologies
PyTorch, Hugging Face, Diffusion models, Flow-based methods, Transformers
Responsibilities
Research and develop generative models for controllable synthesis; Innovate in advanced diffusion and flow-based methods; Advance visual grounding, depth and 3D estimation, segmentation, and matting; Design multimodal GenAI workflows including visual-language model tooling and agentic pipelines.
Seniority
Senior, hands-on IC
