Data Scientist

United Parcel Service, Inc.
Atlanta, GA, United States
1 day ago
Apply on arc.dev
Prepare application

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Job source

Tech stack

Clean Code Principles Java (Programming Language) Microsoft Windows Artificial Intelligence Data Analysis C++ (Programming Language) Cloud Computing Cloud Engineering Data Cleansing Information Engineering Data Visualization Linux
+20 more
Distributed Systems R (Programming Language) Python (Programming Language) Machine Learning Open Source Technology Performance Tuning Cloud Services Tensorflow SQL Databases Test Data Unstructured Data Cloud Platform System Pytorch Keras Information Technology Data Analytics Data Management Machine Learning Operations Unsupervised Learning Databricks

Job description

This Data Scientist creates and implements advanced analytics models and solutions to yield predictive and prescriptive insights from large volumes of structured and unstructured data. This position works with a team responsible for the research and implementation of predictive requirements by leveraging industry standard machine learning and data visualization tools to draw insights that empower confident decisions and product creation. This position leverages emerging tools and technologies available in On-prem and Cloud environments. This position utilizes industry standard machine learning and data visualization tools to transform data and analytics requirements into predictive solutions and provide data literacy on a range of machine learning systems at UPS. This position identifies opportunities for driving descriptive to predictive and prescriptive solutions, which become inputs to department and project teams on their decisions supporting projects., * 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.
  • For larger teams, works with data engineering teams to validate and test data and model pipelines identified during proof of concepts.
  • 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.

Requirements

  • Expertise in R, SQL, Python and/or any other high-level languages.
  • Exploratory data analysis (EDA), data engineering and development of advanced analytics models.
  • Experience in development of AI and ML using platforms like VertexAI, Databricks or Sagemaker, and familiarity with available frameworks like PyTorch, Tensorflow and Keras.
  • Experience applying models from small to medium scaled problems.
  • Strong analytical skills and attention to detail.
  • Able to engage key business and executive-level stakeholders to translate business problems to a high-level analytics solution approach.
  • Expertise with statistical techniques, machine learning, and/or operations research and their application in business.
  • Deep understanding of data management pipelines and experience in launching moderate scale advanced analytics projects in production.
  • 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.
  • Core AI / Machine Learning knowledge and application in supervised and unsupervised learning domains.
  • Familiarity with Java or C++ is a plus.
  • 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 audiences.
  • 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.

About the company

Explore your next opportunity at a Fortune Global 500 organization. Envision innovative possibilities, experience our rewarding culture, and work with talented teams that help you become better every day. We know what it takes to lead UPS into tomorrow-people with a unique combination of skill + passion. If you have the qualities and drive to lead yourself or teams, there are roles ready to cultivate your skills and take you to the next level.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on arc.dev
Prepare application

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

3:14 min

Structuring career paths and localized data architectures

Ulrich Wurstbauer +1 · LIVE

2:35 min

Preventing remote code execution in PyTorch models

Balázs Kiss · World Congress 2023

1:18 min

Converting existing Keras models to TensorFlow format

Håkan Silfvernagel · LIVE

52 sec

Running persistent Linux environments directly on Windows

Ben Breard Ben Breard · World Congress 2025

1:06 min

Compiling PyTorch environments for advanced time forecasting

Christoph Lohrmann Christoph Lohrmann +1 · World Congress 2026 Europe

2:20 min

Speeding up model training cycles with transfer learning techniques

Anirudh Koul · LIVE

Videos

See all

Related articles

See all