Amazon's Similarities team owns innovation for features such as “Frequently Bought Together”, "Customers Who Bought This Item Also Bought", “Customers who viewed this also viewed” that are used by millions of customers each day to discover new products. We own these features end-to-end the algorithms, backend services, frontend UI on mobile and desktop. The team's datasets are at the core of Amazon's collaborative filtering engine which personalizes the Amazon.com website based on the unique interests of each customer.
We build systems to harness the collective intelligence found in the billions of interactions that happen on our global family of websites. Our algorithms seek out the most useful aggregate patterns amongst an enormous sea of noise. These patterns are then made available to the shopping customer who benefits from the experience of millions of customers who came before them.
Our systems operate at massive scale. Our data mining algorithms are able to process billions of transactions made by hundreds of millions of customers on a catalog with hundreds of millions of items. The online services which vend our data get billions of requests per day. That's tens of thousands of requests per second, every second of every day. And, we do it all with a lot less hardware than you think; we take pride in the efficiency of our systems.
We're seeking a skilled and creative software engineer to help invent the future of product discovery.
You're an experienced engineer looking for a career where you'll be able to build, deliver, and impress. You enjoy getting computers to make intelligent decisions in the face of real-world noisy data. You challenge yourself and others to constantly come up with better solutions. You're a thought leader and you demonstrate this by building solutions, not just by having ideas. You develop strong working relationships with others and want to work in a collaborative team environment. You want to create value and make a real impact to the delight of millions of people worldwide.
About us together:
We're going to design and deliver the next generation of recommender systems. Along the way, we're going to face seemingly impossible problems. We're going to argue about how to solve them, and we'll work together to find a solution that is superior to each of the proposals we came in with. We'll make tough decisions, but we'll all understand why. We'll be the dream team.
A few problem spaces we'll be working on:
Algorithm Development - The "customers who bought this item" might have bought 10,000 other distinct items. How do we choose the best 5 to show? This is a very high dimensional space we are optimizing and there is no simple answer to this. Amazon sells an amazingly diverse set of items, from e-books to table saws, and what works for one type of product might not work for others. We are continually experimenting with improvements to our item selection algorithms.
Use Machine Learning to choose the best dataset and UI – Determine what are the best datasets and best presentations for them, to help our customers succeed in their shopping missions.
Scaling, Scaling, Scaling - We have a lot of data. Oh my, we have a lot of data. And it keeps getting bigger. Just staying ahead of Amazon's annual business growth has been a perennial challenge. We keep looking for more efficient ways to run our builds and vend our data using AWS solutions.
The Similarities team works in a fast-paced iterative environment where we can quickly launch experimental features to an audience of millions and learn what works through metrics and explicit feedback. We take these learnings and iterate to arrive at the ideal customer experience. As someone with a passion for building great customer experiences, you'll strongly own what to build.