Software Development Engineer - Machine Learning & Data Mining

Job Number: 78541361 Company Name: Amazon Job Location: Seattle, WA US Job Categories: Information Technology Engineering & Architecture

---

Software Development Engineer - Machine Learning & Data Mining

Overview
Amazon's product recommendations are among our most popular and best-loved features and help drive customer delight by recommending relevant, serendipitous products based on each customer's unique interests.

Spanning academia, research and massive scale real world systems, the Personalization Platform team is responsible for the collection of real-time behavioral data as well as developing recommender systems for Amazon and its subsidiaries. Active research areas include mitigating the cold start problem, dealing with sparse data sets and making recommendations useful for content based sites, apparel, video games and replenishables.

Role
As a Software Development Engineer (SDE) on the Personalization Platform team, you'll be assigned to work in one of two areas: recommender systems or large scale, high throughput behavioral collection data services.

If you join the core recommender systems team, your responsibilities will include working with site owners to understand their discovery challenges and unique customer and catalog data. You'll apply traditional and non-traditional approaches to developing recommender systems, ranging from statistical to machine learning techniques for content based recommenders, contextual based recommenders, user/item based collaborative filtering as well as hybrid recommenders.

If you join the behavioral data collection service team, you'll work closely with internal teams that utilize this data service in order to understand their upcoming requirements and desired improvements. You'll continually investigate ways to extend the service to meet new use cases as well as drive down the cost of the service over time. Our data service is the largest, low latency distributed data service used at Amazon and it enables teams to deliver customer facing features that react to user behavior in real time.

In both roles, you'll stay up to date with the current state of the art by reading academic papers, attending relevant university colloquia and conferences.
Basic Qualifications

• BS in Computer Science or related technical field (MS a plus)
• Minimum of 3 years industry experience as a software developer
• Fluent in Java or C++
• Strong Computer Science fundamentals (data structures & algorithms)
• Strong Object Oriented design skills

Preferred Qualifications

• Experience in recommender systems, data mining, machine learning, or artificial intelligence in a commercial setting (for the core recommender systems role)
  • Knowledge of scalable distributed systems and service oriented architecture
    • Experience with large scale, distributed key/value stores such as memcached/spymemcached (for the behavioral data collection service role)
      • Ability to deal with ambiguity and innovate and simplify
        • Excellent written and oral communication skills
          • Excellent analytical skills
          machine learning, data mining, personalization, recommender systems, similarities, hadoop, mahout, information extraction, sentiment analysis, unsupervised learning, supervised learning, instance based learning, dimensionality reduction, latent factors, NLP
        *LI-DL2

Apply