Software Engineer:Data Mining/Information Retrieval systems on S3 Job in Seattle 98119, Washington US

Software Engineer:Data Mining/Information Retrieval systems on S3

Semantic information extraction, information retrieval and data mining on large data using Amazon's cloud infrastructure

A book has 5 main characters and we have Halloween costumes for all of them. There is a video game based on it. Its movie adaptation was a block buster. It is a seminal work and it has references in these books and movies. Awards it has won, its translations to other languages, controversies and religious debate it generated ...

We want to generate this information not just for books but all of the 100s of millions of items in the Amazon product catalog. The applications of this information to help customers find what they are looking for and delight them with information and products that they did not know were available, are numerous. And we are responsible for building those experiences in addition to generating the data which powers them.

To get there, we are using semantic information extraction, data mining, information retrieval, machine learning and just plain good engineering to build systems that solve these problems at scale. Given the size of data we process, large parts of our systems run on the Amazon cloud infrastructure using Elastic Map Reduce (EMR) and Simple Storage Service (S3) offerings.

If you are excited about solving these cutting edge technical problems, have the desire to see your work having a huge end user impact and are willing to do whatever it takes to get there, we want you.