Sr. Applied Scientist, Prime Video - Personalization and Discovery Science

Amazon Amazon · Big Tech · Seattle, WA · Applied Science

Senior Applied Scientist role focused on developing and launching AI solutions for Prime Video's personalization and discovery systems, utilizing deep learning, GenAI, and reinforcement learning. The role involves end-to-end ownership from design to experimentation and publication of research findings, with a focus on rethinking recommendation systems for adaptive page-level decision-making.

What you'd actually do

  1. Develop AI solutions for various Prime Video Search systems using Deep learning, GenAI, Reinforcement Learning, and optimization methods
  2. Work closely with engineers and product managers to design, implement and launch AI solutions end-to-end
  3. Design and conduct offline and online (A/B) experiments to evaluate proposed solutions based on in-depth data analyses
  4. Effectively communicate technical and non-technical ideas with teammates and stakeholders
  5. Stay up-to-date with advancements and the latest modeling techniques in the field

Skills

Required

  • 3+ years of building machine learning models for business application experience
  • PhD, or Master's degree and 6+ years of applied research experience
  • Experience programming in Java, C++, Python or related language
  • Experience with neural deep learning methods and machine learning

Nice to have

  • Experience with modeling tools such as R, scikit-learn, Spark MLLib, MxNet, Tensorflow, numpy, scipy etc.
  • Experience with large scale distributed systems such as Hadoop, Spark etc.

What the JD emphasized

  • building and guiding machine learning models from the ground up
  • Publish your research findings in top conferences and journals

Other signals

  • Develop AI solutions for various Prime Video Search systems using Deep learning, GenAI, Reinforcement Learning, and optimization methods
  • Work closely with engineers and product managers to design, implement and launch AI solutions end-to-end
  • Design and conduct offline and online (A/B) experiments to evaluate proposed solutions based on in-depth data analyses
  • Stay up-to-date with advancements and the latest modeling techniques in the field
  • Publish your research findings in top conferences and journals
  • Our team works at the intersection of generative recommendations, multi-objective reinforcement learning, and whole-page optimization
  • We're rethinking how recommendation systems construct experiences end-to-end, moving beyond ranked lists toward intelligent, adaptive page-level decision-making at scale