Returning Candidate?

Software Development Engineer - Catalog ML/Image Information Extraction Platform

Software Development Engineer - Catalog ML/Image Information Extraction Platform

Job ID 
Posted Date 
Company Services, Inc.
Position Category 
Software Development
Recruiting Team 
North American Teams - Consumer - Retail Plus

Job Description

Amazon changed the face of retail by changing the way consumers shop and buy. It went from a bookstore to an everything-store with the largest product selection on earth provided by millions of merchants. Amazon strives to ensure that products are organized and represented with accurate information to help customers make the best buying decisions. Yet, products features can be inaccurate or incomplete and shopping is riddled with ambiguity.

The Catalog System & Services team aims to build the next generation of product image information extraction; We want to extract every bit of information from billions of product images to enhance the shopping experience, from product classification to extracting factual information (this is a "blue", "long-sleeve", "v-neck" t-shirt).

If you are excited about making the Amazon catalog more dynamic, smarter and changing the way we understand product images and help customers discover, and purchase products, come join us! We are looking for people with initiative who enjoy diving deep into the data and coming up with innovative solutions. You will find challenges in:

Data Analytics: We build analytical workflows to dig into the huge amounts of data available at Amazon using machine learning and deep-learning. We extract information and patterns from images and use them to discover facts and relationships between products. We collect knowledge from experts and train models that scale it across our catalog.

Scalability: We process billions of records about products every day ranging from electronics to cosmetics. We build highly distributed systems and design algorithms that are able to handle these large amounts of data and operate with latencies in the tens of milliseconds for millions of transactions per second. Where traditional solutions fail we develop approximate, distributed and streaming algorithms.

Basic Qualifications

  • Bachelor's degree in Computer Science or a related field
  • 4 years+ of Software Development Experience
  • Proficiency in at least one modern programming language such as Java, C++, or C#

Preferred Qualifications

  • Advanced post graduate degrees (M.S., Ph.D.) in Computer Science or a related field
  • Experience with Cloud computing (IaaS, PaaS, SaaS), AWS or equivalents
  • Experience in developing large-scale distributed or bigdata solutions on Hadoop using Spark, Scala, Impala & hive
  • Experience in machine learning, data mining, artificial intelligence or statistics