Applied Scientist, Prime Video Science

Description

The Prime Video Science team leverages the latest in machine learning and AI techniques combined with causal inference to bring scientific rigor to the biggest decisions in entertainment: what content to make, what to license, and where to invest. We build large-scale models that simulate how our global customer base responds to change, and we get to see that work shape what the business does.

Prime Video is an industry-leading entertainment business and a critical driver of Amazon Prime subscriptions, contributing to customer loyalty and lifetime value. Our models learn from customer behavior to answer questions the business can't test directly and use those answers to guide where Prime Video invests in content and product. We're looking for an Applied Scientist to help build the next generation of these models.

As an Applied Scientist on this team, you will build machine learning and deep learning models on large-scale global data to simulate customer behavior across the business. Ideally you bring experience with reinforcement learning, causal inference, and/or the design of agentic AI systems. You will partner closely with business, finance, engineering, and science stakeholders to take ideas from concept and prototype through to production.

The candidate should have strong communication skills and the ability to translate data-driven findings into actionable insights. The successful candidate will be a self-starter comfortable with ambiguity, with strong attention to detail and the ability to work in a fast-paced and ever-changing environment.

• Build models that simulate customer behavior to answer counterfactual  what-if  questions that guide major content and product investment decisions.
• Apply deep learning, reinforcement learning, causal inference, and experimental design to large-scale customer data to model how customers respond to change.
• Design and prototype agentic AI systems and other novel ML approaches and research new methods to improve the accuracy and scale of our models.
• Validate and calibrate models against real-world randomized experiments, and partner with software engineers to deliver scalable, production-ready systems.
• Translate model outputs into clear recommendations and communicate results to business, finance, and science stakeholders through both technical papers and business-facing documents.

The Prime Video Science team is a multidisciplinary group of applied scientists, data scientists, economists, and engineers. We take on some of the hardest research questions in the business, and our work carries visibility up to the CFO/CEO level. We pursue ambitious research at the intersection of machine learning, AI, and causal inference, turning that research into innovations that improve customer experience and strengthen business profitability.

Few science teams get to work on problems this hard and this impactful; if that combination excites you, we'd love to talk.

• 3+ years of building machine learning models or developing algorithms for business application experience
• PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience
• Experience in patents or publications at top-tier peer-reviewed conferences or journals
• Experience programming in Java, C++, Python or related language

• Experience in state-of-the-art deep learning models architecture design and deep learning training and optimization and model pruning
• Experience in investigating, designing, prototyping, and delivering new and innovative system solutions
• Experience in professional software development
• Experience with reinforcement learning, agentic AI system design and/or causal inference

Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.

Los Angeles County applicants:
Job duties for this position include: work safely and cooperatively with other employees, supervisors, and staff; adhere to standards of excellence despite stressful conditions; communicate effectively and respectfully with employees,…