Amazon
Sr. Applied Scientist, Prime Video - Personalization and Discovery Science, Prime Video - Personalization and Discovery Science
$167K–$260K
Sunnyvale, CA +2 · Senior · Full-time · Posted Aug 31, 2026
- Location
- Sunnyvale, CA
Seattle, WA
New York, NY - Experience
- 3+ years building machine learning models for business applications; alternatively, PhD or Master's degree and 6+ years of applied research experience.
- Education
- PhD, or Master's degree.
About the job
Develops machine learning models for Prime Video content understanding, customer behavior prediction, recommendations, and personalization, and evaluates and launches solutions with engineering and product teams.
What you'll do
- Develop deep learning and multimodal foundation models to analyze video, audio, and text, and time-sequence models to predict viewing behavior.
- Design and conduct offline and online A/B experiments, analyze results, and work with engineering and product teams to launch solutions.
- Communicate findings, stay current with modeling research, and publish research in conferences and journals.
What they ask for
- 3+ years of building machine learning models for business application experience.
- PhD, or Master's degree and 6+ years of applied research experience.
- Programming experience in Java, C++, Python or related language.
- Experience with neural deep learning methods and machine learning.
Nice to have
- Experience with R, scikit-learn, Spark MLLib, MxNet, Tensorflow, numpy, or scipy.
- Experience with large scale distributed systems such as Hadoop or Spark.
Pay
192,200.00 - 260,000.00 USD annually (base salary); 183,800.00 - 248,700.00 USD annually (base salary); 167,100.00 - 226,100.00 USD annually (base salary)
Tools
Java, C++, Python, R, scikit-learn, Spark MLLib, Tensorflow, Hadoop
AI focus
Build foundation models using deep learning and multimodal learning for content understanding, and time-sequence foundation models to understand and predict customer behavior and viewing trajectories.
Model-written summary · the original posting is authoritative