Applied Scientist: Live Video Data & Content Intelligence

Amazon Science; Seattle (WA); On-site; USD 143,000 - 193,000; Full time

Job summary

Amazon Live is seeking an Applied Scientist to join the DESA team and build production-grade models, experiments, and signals that close these gaps. You will own problems end-to-end—from framing the research question through model deployment and A/B experimentation—working alongside Data Engineers and a BIE for executive reporting.

Your outputs will not sit in notebooks but run in production, feed ranking systems, power brand-facing metrics, and influence multi-million dollar business decisions.

Qualifications

• PhD or Masters with 4+ years in CS/CE/ML or related field.
• 3+ years building models for business applications.
• Experience in Java, C++, Python; PyTorch or JAX.
• Experience with A/B testing and large-scale distributed systems.
• Experience with causal inference methods.

Responsibilities

• Design and deploy causal attribution models (incrementality testing, multi-touch).
• Develop brand lifecycle and campaign optimization models to scale revenue.
• Design and run A/B experiments for new product surfaces and ranking changes.
• Build multimodal and generative models for content intelligence at scale.
• Develop ranking and personalization features for downstream systems.
• Build predictive models proving video value to programmatic systems.
• Own full lifecycle from research question through production deployment and iteration.
• Present findings to senior leadership and partner teams.
• Contribute to internal publications and cross-team methodology sharing.

Skills

Modeling for business

Java

C++

Python

PyTorch/JAX

A/B testing

Causal inference

Education

PhD or Masters + 4+ years CS/CE/ML

Tools

Hadoop

Spark

Job description

Amazon Live is seeking an Applied Scientist to join the DESA team and build production-grade models, experiments, and signals that close these gaps. You will own problems end-to-end—from framing the research question through model deployment and A/B experimentation—working alongside Data Engineers and a BIE for executive reporting.

Your outputs will not sit in notebooks but run in production, feed ranking systems, power brand-facing metrics, and influence multi-million dollar business decisions.