Senior Applied Scientist , Sponsored Products and Brands Ads Response Prediction

Amazon Amazon · Big Tech · Palo Alto, CA · Applied Science

This role focuses on developing and deploying machine learning and generative AI models for Amazon's Sponsored Products and Brands Ads, aiming to personalize advertising experiences and optimize the ad-serving process. It involves data analysis, model development, A/B testing, and research into new AI solutions, with a strong emphasis on productionizing these models for a large-scale consumer product.

What you'd actually do

  1. Conduct deep data analysis to derive insights to the business, and identify gaps and new opportunities
  2. Develop scalable and effective machine-learning models and optimization strategies to solve business problems
  3. Run regular A/B experiments, gather data, and perform statistical analysis
  4. Work closely with software engineers to deliver end-to-end solutions into production
  5. Improve the scalability, efficiency and automation of large-scale data analytics, model training, deployment and serving
  6. Conduct research on new machine-learning modeling and Generative AI solutions to optimize all aspects of Sponsored Products and Brands business

Skills

Required

  • 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

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

What the JD emphasized

  • building machine learning models for business application experience

Other signals

  • develop scalable and effective machine-learning models
  • improve the scalability, efficiency and automation of large-scale data analytics, model training, deployment and serving
  • advancing response prediction through model and feature innovations
  • extending prediction beyond the auction stage to areas such as targeting, sourcing, and bidding