Senior Generative AI Scientist - Video & Visual Tech

Amazon; New York (NY); On-site; USD 184,000 - 249,000; Full time

Benefits offered by this job

Health insurance

RSUs

Sign-on bonus

Job summary

Amazon’s Prime Video team in New York seeks a Senior Applied Scientist to advance Generative AI for video. You will own research and production systems, applying state-of-the-art ML to visual understanding and generation.

The role emphasizes building controllable diffusion/flow models, 3D/video synthesis, and end-to-end opportunities across models and pipelines, with competitive compensation including RSUs and sign-on payments.

Qualifications

• PhD, or Master’s degree with 6+ years of applied research experience.
• 3+ years 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.

Responsibilities

• Own the product, related research and experimentation; apply advanced ML techniques in CV, multimedia understanding and Generative AI.
• Research and develop generative models for controllable synthesis across images, video, vector graphics, and multimedia.
• Advance visual grounding, depth estimation, segmentation, and matting for integration into pre-visualization, compositing, VFX, and post-production pipelines.
• Design multimodal GenAI workflows including visual-language model tooling and structured prompt orchestration.

Skills

Generative AI

Computer Vision

Machine Learning

Java

Python

C++

Diffusion models

Video synthesis

3D/4D modeling

Education

PhD or Master’s degree

Tools

PyTorch

TensorFlow

CUDA

Diffusion toolkits

Job description

Amazon’s Prime Video team in New York seeks a Senior Applied Scientist to advance Generative AI for video. You will own research and production systems, applying state-of-the-art ML to visual understanding and generation.

The role emphasizes building controllable diffusion/flow models, 3D/video synthesis, and end-to-end opportunities across models and pipelines, with competitive compensation including RSUs and sign-on payments.