Generative AI Scientist for Video & Visual Content

Amazon; Sunnyvale (CA); Hybrid; USD 192,000 - 260,000; Full time

Benefits offered by this job

Health insurance

RSUs

401(k) matching

Paid time off

Parental leave

Job summary

Amazon Prime Video seeks a Sr. Applied Scientist to advance Generative AI for video content.

You will own research and production-ready systems in computer vision and multimedia understanding, developing controllable synthesis and multimodal GenAI workflows. You will collaborate across teams to push state‑of‑the‑art models, optimize for scalability at Amazon scale, and contribute to localization, personalization, and post‑production pipelines.

Qualifications

• PhD or Master's degree with 6+ years of applied research experience.
• 3+ years of building ML models for business applications.
• Experience programming in Java, C++, Python or related language.
• Experience in generative models (diffusion, flow, transformers).
• Hands-on experience with image/video synthesis and editing techniques.
• Proficiency in PyTorch and modern DL toolkits (Hugging Face ecosystem).

Responsibilities

• Research and develop generative models for controllable synthesis across images, video, vector graphics, and multimedia.
• Innovate in diffusion and flow-based methods to improve efficiency, controllability, and scalability.
• Advance visual grounding, depth and 3D estimation, segmentation, and matting for integration into pipelines.
• Design multimodal GenAI workflows including visual-language model tooling and orchestrated pipelines.

Skills

Java

C++

Python

PyTorch

Generative AI

Video synthesis

Education

PhD or Master's

Tools

Hugging Face ecosystem

Job description

Amazon Prime Video seeks a Sr. Applied Scientist to advance Generative AI for video content.

You will own research and production-ready systems in computer vision and multimedia understanding, developing controllable synthesis and multimodal GenAI workflows. You will collaborate across teams to push state‑of‑the‑art models, optimize for scalability at Amazon scale, and contribute to localization, personalization, and post‑production pipelines.