The Amazon Fashion catalog spans millions of items and variations ranging from high fashion to everyday wear. With a large, varied, and growing selection, we are looking for innovative ways to build a catalog that represents a single source of truth to drive product discovery, personalization, and a world-class customer experience.
Downstream systems such as product recommenders and critical browsing experiences are dependent upon high quality catalog attributes. To optimize our catalog, we will need to manage massive quantities of data, apply machine learning at scale, and work cross functionally with front-end teams, product teams, and scientists.
The Amazon Fashion Catalog team is looking for an experienced Software Development Engineer to build and deploy algorithmic solutions to improve/consolidate our catalog and connect customers to the products they love. You will be part of a multidisciplinary and scrappy team of applied ML scientists, business intelligence engineers, and product managers collaborating to build systems that will impact millions of customers.
The ideal candidate is a full stack developer with a bent towards modern big data and machine learning frameworks. They should be comfortable working with very large-scale unstructured data and understand the practical concerns of data storage and processing in production. They should be able to communicate technical details to a non-technical audience and challenge assumptions when necessary. This candidate exemplifies bias for action, the desire to continuously invent and simplify, and most importantly, a genuine curiosity and passion for learning.
Roles and Responsibilities:
· Responsible for the practical implementation, deployment, and maintenance of ML-based models and other features that improve and consolidate the catalog
· Work cross-functionally with scientists and product managers to define problem statements and design/implement solutions
· Assist in the scrum process and operational project planning
· Use data to analyze catalog opportunities and detect anomalies