Software Development Engineer, Browse

Sep 20, 2012
Oct 20, 2012
. .
Full Time
Automatic Browse Classification is doing exciting projects to improve's end user experience. We build highly scalable systems that use Amazon's EMR and DynamoDB frameworks. We use innovative techniques to enhance visibility of items in catalog and eventually ease customer's experience in browsing Amazon's catalog. Our projects involve working on a variety of tasks that involves solving challenges in machine learning, information-retrieval, search relevance, natural language processing, massive scalability, storage solutions, high throughput and low latency website facing distributed services.

You'll work on creating scalable and maintainable software that has a high quality bar. It is your chance to gain working familiarity with a variety of document classification algorithms, ranging from naive bayesian to Vowpal Wabbit. You'll build system that serve algorithms for improving recall of classification algorithms with high accuracy constraints. Automatic Browse Classification presents a unique opportunity to machine learning enthusiasts to learn and practice their passion.

  • Bachelor's Degree in Computer Science along with 4+ years of relevant experience
  • Proficiency in object oriented programming in Java /C C++ programming in a Unix environment.
  • Strong OO Design, Data Structures and Algorithm skills required.

The ideal candidate will also have:

  • Advanced/Masters/Phd in Computer science with related work experience
  • Domain expertise in ONE OR MORE of the following fields:
    • Big data
    • Distributed systems
    • Map - reduce / Hadoop
    • Nosql
  • Experience in a highly scalable, distributed environment preferred.
  • Proven track record of architecting and building scalable systems
  • Results oriented person with a delivery focus.
  • Ability to handle multiple competing priorities in a fast-paced environment.