Data Science Engineer

At Motiva, our employees' energy, passion, and dedication to excellence are what make us who we are and what allows us to generate energy that makes a house a home, gets us from point A to point B, and enables our health and wellbeing. We invest in every aspect of our employees' lives because, at Motiva, our people matter.

Headquartered in Houston, Texas, Motiva refines, distributes and markets petroleum products throughout the Americas. The company's Port Arthur Manufacturing Complex in Port Arthur, TX, is comprised of North America's largest refinery with a total throughput of 720,000 barrels per day, the largest base oil plant in the western hemisphere, and an integrated chemical plant. Under exclusive long-term brand licenses with Shell and Phillips 66 (for the 76®brand), Motiva's commercial operations supply more than 12 billion gallons of fuel to customers annually. Motiva is wholly owned by Aramco, one of the world's largest integrated energy and chemicals companies.

Position Overview :

We are looking for a motivated and curious Junior Data & AI Associate to join our growing AI team. This early career role offers a unique opportunity to contribute across the entire lifecycle of data science and data engineering projects - from exploration and discovery to deployment and monitoring.

Working closely with a small, cross-functional team of data scientists, engineers, and domain experts, you will assist in developing data-driven solutions, building pipelines, and supporting the operationalization of machine learning and reporting use cases.

Responsibilities :

• Develop, test, and deploy data pipelines and ETL processes using Python and data from various sources and formats e.g. JSON, XML, CSV, etc. Collaborate on building and maintaining data pipelines and APIs for model deployment
• Support data analysis, data profiling, feature engineering, and hypothesis testing with reporting and visualization using Python, PowerBI and other tools
• Perform data cleansing / validation, integration and preprocessing activities for exploratory data analysis using Python libraries, such as pandas, numpy, etc.
• Manage Python environments, library installations, and resolve any conflicts, ensuring a stable development platform.
• Contribute to early-stage prototyping and research of AI / ML models. Working with text and unstructured data to use in natural language related models. Support integration of models into applications or dashboards
• Implement and maintain a suite of unit tests using Python testing frameworks such as unittest, pytest, and libraries like mock for creating mock objects and test doubles.
• Optimize data pipelines and systems for performance, scalability, and security documenting data sources, processes, and findings. Help monitor model performance and data drift over time

Experience and Qualifications :

Required Education and Experience :

We reserve the right to amend or withdraw Motiva jobs at any time, including prior to the closing date. Depending on qualifications, the successful candidate may be offered a position at a more appropriate level and / or grade.

Applicants for regular U.S. positions must be authorized to work in the United States for Motiva Enterprises LLC without the need for sponsorship of an immigration authorization or visa (for example, TN, H-1B, or other employment-based immigration authorization or visa).

Motiva participates in E-Verify.

All qualified applicants will receive consideration for employment without regard to race, color, sex, national origin, age, religion, disability, sexual orientation, gender identity, protected veteran status, citizenship, genetic information, or other protected status under federal, state, or local laws.