Applied Scientist, Amazon Ads, Demand Forecasting & Guidance

About The Team

You'll join a highly motivated, collaborative, and entrepreneurial team with a broad mandate to experiment, innovate, and break new ground. Here, your work will directly influence advertiser success and shape the future of programmatic advertising.

Key Job Responsibilities

• Lead and contribute to end-to-end ML initiatives with high ambiguity, scale, and complexity from problem formulation through production deployment
• Develop and optimize forecasting models by performing hands-on analysis of large-scale datasets to improve ad delivery prediction accuracy and operational efficiency
• Build, experiment, and deploy machine learning models through rapid prototyping, rigorous experimentation, and close collaboration with software engineering teams for seamless productization
• Design and execute A/B experiments, collect performance data, and conduct statistical analysis to validate model impact
• Establish scalable ML infrastructure including automated pipelines for data processing, model training, validation, and serving
• Advance the state of the art by researching innovative machine learning techniques and applying them to forecasting challenges

Basic Qualifications

• 3+ years of building models for business application experience
• PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience
• Experience programming in Java, C++, Python or related language
• Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing

Preferred Qualifications

• Experience in designing experiments and statistical analysis of results
• Experience with popular deep learning frameworks such as MxNet and Tensor Flow