Amazon product search, one of the most heavily used services in the world, indexes billions of products and serves hundreds of millions of customers world-wide daily. We are working on a new initiative to transform our search engine into a shopping engine that assists customers with their shopping missions. Understanding the semantic meanings of the customer queries is the critical first step in this new initiative. This is a rare opportunity to develop cut edge Machine Learning algorithms to perform Natural Language Understanding and build top tier distributed service to serve the algorithms at Amazon scale. Some exciting questions that we expect to answer over the next few years include:
- Can we understand and parse 100% of customer queries and understand meanings of each query term (product type, brand, model, etc)?
- Can we build a comprehensive knowledge graph and transform Amazon Search from a word matching engine to a knowledge engine? Can we answer questions such as 'the medicine that relieves anxiety'?
- Can we build scalable online deep learning service for large GPU models such as BERT models? Can we make this inference engine available for other teams inside Amazon? The online inferencing system puts challenges in many ways. How to build efficient systems across heterogenous hardware architecture involving CPUs and GPUs? How to build optimized services that serves billions of requests daily with load latency and high resiliency? How to architect the system that it can support use cases from different teams of Amazon, including search, Ads, and Alexa? How to build automated infrastructure to leverage the transfer learning capability of the DL models for new marketplaces?
- Can we develop scalable solutions to handle 39+ different languages worldwide? Can we leverage state-of-art research in transfer learning to solve the multi-lingual search at scale?
- Can we build next generation user interaction experience such as conversational shopping?
As an engineer on the team, you will define, design and implement key initiatives in building the new DL systems that powers search, sponsored products, Alexa and many other downstream applications; work closely with other applied scientists, engineers, engineering and product managers to drive new enhancements to the system; design and build machine learning platform that powers deep learning; work with various AWS technologies and distributed computing technologies; build a robust, scalable and an extensible platform which supports large scale data analyses, model development, training, validation and implementation.
You will love this role because you will:
- Make billion dollar impact to Amazon's retail business worldwide;
- Work on a world-class Query Understanding service that handles billions of requests per day and is an important component of Amazon Product Search;
- Figure out creative ways to make AWS and NLP/ML technology work at production scale;
- Gain exposure to the workings of the largest e-commerce search engine and an opportunity to work with a dynamic team to define and develop innovative solutions that will have a direct impact on Amazon product search;
- Close interactions with applied scientists to apply research to production and publish papers in top conferences;
- Work with large data sets to analyze and improve the search experience using various AWS technologies;
- Have access to Amazon's vast technical resources to get the job done;
At Amazon Search, you'll experience the benefits of working in a dynamic, entrepreneurial environment, while leveraging the resources of Amazon.com (AMZN), one of the world's leading internet companies.
• 2+ years of non-internship professional software development experience
• Programming experience with at least one modern language such as Java, C++, or C# including object-oriented design
• 1+ years of experience contributing to the architecture and design (architecture, design patterns, reliability and scaling) of new and current systems.
• Bachelor's degree in Computer Science or related technical fields
• A minimum 2 years of hands-on experience with Information Retrieval and large-scale geographic, location and mapping technologies
• Advanced Degree in Computer Science or related fields
• Computer Science fundamentals in data structures, algorithm design, and complexity analysis.
• Interest in Search, Machine Learning, and Natural Language Processing.
• Experience in Search, A/B experimentation, Distributed Computing, Data Analysis, Information Retrieval.
• Experience presenting complex technical information in a clear and concise manner to a variety of audiences.
• Strong verbal and written communications skills, as well as the ability to work effectively across internal and external organizations
• Track record of project delivery for large, cross-functional projects.
• Aptitude for motivating and inspiring a team.
• Ability to handle multiple competing priorities in a fast-paced environment.
• A passion for innovation