Are you excited and passionate about delivering advanced analytics that directly influence the Fashion shopping experience? Do you see yourself as a champion of innovating on behalf of the customer by turning data insights into action? Come join Fashion Science team as Data Scientist.
The Fashion Science team at Amazon aims to make Amazon the number one online shopping destination for Fashion by creating products, processes, tools, and platforms to support innovative and engaging fashion experiences. We are seeking a Data Scientist who has a solid background in database, hypothesis data, data mining, applied machine learning, deep passion for building data-driven products and has a history of executing complex projects and deliver solutions that directly impact customers.
Fashion is extremely fast-moving, visual, subjective, and it presents numerous unique challenges in areas such as product recommendations, product discovery, and data quality. The Fashion Science team builds large-scale machine learning systems to solve these challenges. We leverage the massive computing power of Amazon Web Services as well as big data technologies such as Spark and Hadoop to build data pipelines for hundreds of millions of products. Our data is used by numerous front-end teams to deliver loved experiences to customers all around the world.
This role is part of Fashion Scientist team that is responsible for building Machine learning models for customer facing products. What is that you will do in this role? You will work with the scientists and engineers in this team to influence how the database and dataflow are designed for the ML production pipeline. You will also work with PMs to drive data-driven, customer-centric decisions, including diving deep dive into weblab results, customer feedback and interactions, and identify areas of opportunities.
Key Responsibilities include:
§ Design and build data architecture to extract data for decision making.
§ Study, and understand the business requirements for data.
§ Taking a data-driven approach to evaluate products and ML models work and identify areas of improvements.
§ Contribute to the overall product roadmap, manage prioritization and trade-offs against customer experience, and time to market. Also, create, enhance, and maintain technical documentation, and present to other scientists and business leaders.
· Masters with two years of experience or a Bachelor’s degree in Statistics, Applied Math, Operations Research, Economics, Engineering or a related quantitative field with five years of working experience as a Data Scientist
· Experience with statistical analysis, data modeling, regression modeling and forecasting, time series analysis, data mining, financial analysis, and demand modeling
· Experience applying various machine learning techniques, and understanding the key parameters that affect their performance
· Experience in Statistical Software such as R, Weka, SAS, SPSS
· Proficiency with TABLEAU/R or other web based interfaces to create graphic-rich customizable plots, charts data maps, etc.
· Able to write SQL scripts for analysis and reporting (Redshift, SQL, MySQL)
· Experience using one or more Python, R, Java, C++, VBA, and other programming languages
· Experience processing, filtering, and presenting large quantities (100K to Millions of rows) of data
· Previous experience in a ML or data scientist role with a large technology company
· Ability to develop experimental and analytic plans for data modeling processes, use of strong baselines, ability to accurately determine cause and effect relations
· Experience in creating data driven visualizations to describe an end-to-end system
· Excellent written and verbal communication skills. The role requires effective communication with colleagues from computer science, operations research and business backgrounds.
Amazon is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation.