At Amazon, we are the most customer-centric company on earth. If you'd like to help us build the place to find and buy anything online, this is your chance to make history. To get there, we need exceptionally talented, bright, and driven people. We are looking for a dynamic, organized self-starter to join as an Applied Scientist II for Promise Optimization.
The Promise Optimization team seeks to identify the optimal delivery option for whatever a customer wants. We believe that finding an optimal promise and living up to it consistently improves our customer experience because we increase customer's confidence and trust in Amazon as the one, best option to get what you want, when you want it.
As the applied scientist for Promise Optimization, you will be responsible for building and productionizing machine learning models to answer predictive questions and lead efforts to scale, automate, and productionize statistical models on the impact of delivery speed on customer behavior. You will work with a diverse scientific team including software engineers, economists, and data engineers.
Within predictive analytics, you will develop and implement a missed promise prediction model in production software. This model will inform supply chain systems on the risk of late shipments throughout the order lifecycle, unlocking the ability for fulfillment execution risk to be known and addressed from promise through fulfillment. Other predictive questions you may address involve predicting shipment consolidations and customer contacts following missed promises. In each case, you will balance analytical rigor with pragmatism, focusing on delivering value for the business question at hand.
As our team’s work on estimating the value of delivery speed is incorporated in production software worldwide, you will work with economists to scale and automate statistical models using big data technologies such as Spark and EMR. Your expertise will be used to instruct researchers on using these same technologies, helping to leverage scarce research headcount. You will be a standard bearer on engineering best practices for production models and serve as a technical liaison to the software engineers whose systems depend on our models.
· Working with economists, BIEs, DEs, and SDEs to design, test, implement, and support predictive and operations research optimization models in production software environments
· Ensuring that production models are robust, scalable, and address business and software engineering requirements
· Using big data and AWS technologies to scale, automate, and productionize core statistical models and enable rapid deployment of refreshed models, as well as instructing other researchers on the use of these tools
· Recognizing and adopting best practices in analysis, data and model integrity, test design, validation, and documentation
Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation
· Ph.D. in Computer Science, Operations Research, Statistics, Applied Mathematics, or a related field and 3 years work experience
· Experience with big data technologies (Spark, EMR, Hadoop, etc.) and AWS services (S3, DynamoDB, Lambda, etc.)
· Proven track record of production achievements, handling gigabyte and terabyte size datasets
· Strong personal interest in learning, researching, and creating new technologies with high customer impact
· Master’s degree in Computer Science, Computer Engineering, Mathematics, Economics, Operations Research, Statistics, or related technical field, or equivalent work experience
· At least 2 years of relevant work experience in analytics, software engineering, business intelligence, or related field
· Knowledge of standard machine learning concepts and models
· Experience in designing analytic and/or algorithmic solutions to business or operational problems
· Knowledge of statistical programming language such as R or Python
· Effective communication and strong collaboration skills with research, engineering, and product management teams