We're looking for an Applied Scientist to optimize prediction, ranking and bidding for Amazon's programmatic advertising product. In this role you will work at the forefront of high scale low latency customer-facing advertising systems, mixing machine learning, game theory and feedback control. Your work will affect multi-billion dollar businesses, and you will be responsible for designing, testing and delivering significant breakthrough's for Amazon's business.
Key job responsibilities
* Design and implement auctions for scaled self-serve display advertising.
* Own the allocation and pricing decision for hundreds of thousdands of candidate ads with diverse objectives across highly varied supply types.
* Invent new auction types and controls for advertisers that balance value for shoppers, advertisers and Amazon.
* Be immersed in Amazon's advertisers and their objectives, and think long-term about how to turn those objectives into products and technical capabilities
* Understand the latest literature on auction theory, machine learning and measurement to guide strategic investment for the organization
A day in the life
* Be immersed in Sponsored Display's auction data: candidate ads, objectives, bids and outcomes
* Design, prototype and validate new auction mechanisms or parameterizations
* Take technical leadership over turning prototypes into shopper- and advertiser-facing software
* Stay abreast of the latest trends and opportunities in machine learning, economics, auction theory and measurement
* Be an advocate and expert for SD's auction to leaders and stakeholders inside and outside advertising
About the team
Sponsored Display is a rapidly growing advertising product that aims to bring Display-style advertising to self-serve advertisers of any size. We're a customer-focused product powered by deep, exciting technology. We bias towards disruptive innovation that affects the experiences of all our advertisers and shoppers worldwide. We are deeply flexible in technology and methods, prefer multi-displicplinary collaborations and broad viewpoints, and are obsessed over cutting edge research in customer-facing software and products.
BASIC QUALIFICATIONS
- Master's degree
- Experience programming in Java, C++, Python or related language
- Experience with neural deep learning methods and machine learning
- Experience in building machine learning models for business application
- Experience in applied research
PREFERRED QUALIFICATIONS
- 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.