Applied Scientist, Prime Video - Content Localization, Understanding & Enrichment
Core
Applying state-of-the-art natural language processing and computer vision research to video-centric digital media for content understanding and enrichment.
Role type
Applied Scientist (Multimodal ML)
Builds
Multi-modal machine learning technologies for video content understanding, search, and localization.
Domain
Streaming media, Computer Vision, Natural Language Processing
Deliverable
production ML models
Required skills
Vision-language models, Multimodal LLMs, Long-form content understanding, Long-context architectures, Causal reasoning, Deep learning algorithms, Computer vision algorithms
Preferred skills
Unix/Linux, Professional software development, Top-tier conference publications
Technologies
Java, C++, Python
Responsibilities
Develop and implement deep learning algorithms for computer vision; Build models for business applications; Create architectures handling long-context understanding and causal reasoning across temporal sequences.
Seniority
Mid-Senior, hands-on IC
