Data Scientist

Key Skills

PHP Programming, Ruby on Rails, Java Programming, Python Programming, .NET, C Programming, Framework, SQL, Azure, AWS, GoLang

Job Description

We’re the obstacle overcomers, the problem get-arounders. From figuring it out to getting it done… our innovative culture demands “yes and how!” We are UPS. We are the United Problem Solvers.

Will consider candidates from the following I.T. locations: NJ, GA, and KY.

About Data Science at UPS Technology:

The Data Scientist will work with our AAG DSML CoE team to create, develop and deliver machine learning models that would be needed to support business decisions. The teams are responsible for designing and supporting data solutions to meet UPS’s rapidly changing business needs. Our team is comprised of individuals who are experts in data analysis, data mining, predictive and prescriptive analytics. We ensure quality, completeness, availability, protection, understanding and effective use of our data assets. Our ability to organize and design data provides the foundation which enables many of UPS’ core processes.

The Data Scientist gathers data and performs analysis necessary to develop and evaluate UPS Strategy. Successful candidate will work under supervision of a Senior Data Scientist and a team lead, as well as internal Subject Matter Experts to assist in identifying the best approach to gathering information and solving business issues in various areas of UPS business, ranging from Customer Accounts to Package Delivery to Workforce Analytics. The candidate will possess ability to demonstrate experience with analytics, data gathering and data mining tools to assist in guiding the business strategy.

Responsibilities include:

• Defines key data sources from UPS and external sources to deliver models.
• Develops and implements pipelines that facilitates data cleansing, data transformations, data enrichments from multiple sources (internal and external) that serve as inputs for data and analytics systems.
• Develops data design based on the exploratory analysis of large amounts of data to discover trends and patterns that meet stated business needs.
• Defines model key performance indicator (KPI) expectations and validation, testing, and re-training of existing models to meet business objectives.
• Reviews and creates repeatable solutions through written project documentation, process flowcharts, logs, and commented clean code to produce datasets that can be used in analytics and/or predictive modeling.
• Synthesizes insights and documents findings through clear and concise presentations and reports to stakeholders.
• Presents operationalized analytic findings and provides recommendations.
• Incorporates best practices on the use of statistical modeling, machine learning algorithms, distributed computing, cloud-based AI technologies, and run time performance tuning with the goal of deployment and market introduction
• Leverages emerging tools and technologies together with the use of open-source or vendor products in the creation and delivery of insights that support predictive and prescriptive solutions
• Evaluates the quality of data, models and algorithms and collaborates with senior/lead Data Scientists and Machine Learning Engineers for model maintenance and adjustments over time
• Collaborates with Senior/Lead Data Scientists, Machine Learning Engineers in tracking and quantifying value of models
• Collaborates with Senior/Lead Data Scientist to promote the adoption of models and/or ML techniques for business partners

Minimum Requirements:

• Experience in collection of data from disparate sources and rapidly analyze and create presentations that would highlight insights to both technical and non-technical audience
• Familiarity with use of Machine Learning techniques and algorithms used for building Classification and Regression models. Use of Deep Learning techniques for both analyzing data and gaining the insights. Frameworks like Pytorch and Tensorflow
• Strong general programming skills in Linux, along with knowledge of programming languages such as Java and XML (for data description), Python (for creating and analyzing volumetric data), Ruby, Golang, PHP and .NET (as a framework)
• Demonstrated experience in Cloud-AI technologies and knowledge of environments both in Linux/Unix and Windows.
• Experience implementing open-source technologies and cloud services; with or without the use of enterprise data science platforms (through Python, Java, C)
• Knowledge of Cloud Platforms like Azure, Google or AWS in assisting producing exploratory and descriptive reports on multi-million rows of data
• Solid oral and written communication skills, especially around analytical concepts and methods.
• Ability to communicate data through a story framework to convey data-driven results to technical and non-technical audience. 
• Master’s Degree in a quantitative field of mathematics, computer science, physics, economics, engineering, statistics (operations research, quantitative social science, etc.), international equivalent, or equivalent job experience