Software Development Engineer, Amazon Search Autocomplete and Navigation AI
Summary
Builds AI-powered search navigation systems that refine customer queries into relevant product suggestions, processing billions of daily searches with scalable data pipelines and real-time models.
The Amazon Search Autocomplete and Navigation AI team is on a mission to help customer narrow down from their search intent to a handful products for making their final purchase decisions. The team generates highly relevant, context-aware, and personalized search refinements, optimizing their presentation order in a variety of Search Navigation UIs and guiding users to the most relevant search results. The team also owns navigation P0 metrics and defect guardrails to ensure performance and reliability. Additionally, the team develops and maintains engineering infrastructures, such as the Navigation Experience Service (NES) and Alster Refinement Provider Service (ARPS). These services connect to related search systems, serving 3B+ queries worldwide daily. They also support launches of new navigation contents and UIs and enable rapid experimentation both offline and online.
This role requires a pragmatic problem solver comfortable with ambiguity, with deep expertise in data processing at scale. A candidate will need to leverage a wide range of skills and best practices including an emphasis on data processing at scale in customer-facing applications. Additionally, we are seeking candidates with determination and rigor in engineering, deep curiosity and interest for applied sciences, creativity, and sound logic and reasoning.
Key job responsibilities
In this role you will leverage your engineering background and expertise to help build the next generation of our mission understanding models and data collection framework. On a day-to-day basis, you will:
* Interface with Applied Scientists, Product Managers, and Program Managers to determine requirements for production systems
* Analyze log data to determine future system design and configure parameters
Build scalable and production-ready data pipelines to extract features from petabytes of raw data
Integrate models and algorithms in complex, real-time production systems on immense scale
* Design and execute experiments to determine the impact of models and algorithms you intend to deploy in production
* Run analysis reports of web-experiments to identify benefits and risk of launching the models and algorithms
* Serve as a liaison to our customer/seller-facing partner teams in case of escalations
Project manage cross-functional Machine Learning initiatives
This role requires a pragmatic problem solver comfortable with ambiguity, with deep expertise in data processing at scale. A candidate will need to leverage a wide range of skills and best practices including an emphasis on data processing at scale in customer-facing applications. Additionally, we are seeking candidates with determination and rigor in engineering, deep curiosity and interest for applied sciences, creativity, and sound logic and reasoning.
Key job responsibilities
In this role you will leverage your engineering background and expertise to help build the next generation of our mission understanding models and data collection framework. On a day-to-day basis, you will:
* Interface with Applied Scientists, Product Managers, and Program Managers to determine requirements for production systems
* Analyze log data to determine future system design and configure parameters
Build scalable and production-ready data pipelines to extract features from petabytes of raw data
Integrate models and algorithms in complex, real-time production systems on immense scale
* Design and execute experiments to determine the impact of models and algorithms you intend to deploy in production
* Run analysis reports of web-experiments to identify benefits and risk of launching the models and algorithms
* Serve as a liaison to our customer/seller-facing partner teams in case of escalations
Project manage cross-functional Machine Learning initiatives