Data Modeler III

Title: Data Modeler III

Location: Houston, TX

Duration: 1 year (with possible extension)

Work Model: Hybrid (Mon, Tues, Thurs in office / Weds, Fri at home)

High Level Job Description

SCM Data, Innovation & analytics is seeking a Data modeler with strong Databricks expertise to design, build, and operationalize scalable Supply Chain data products that deliver measurable business value for Supply Chain. The role combines advanced analytics, data pipeline development, and product delivery to turn complex SCM data into trusted, governed, and actionable insights.

Specific Accountability

* Develop analytics solutions that address Supply Chain business problems, leveraging knowledge of oil & gas operations, procurement, supplier performance, spend analytics, and enterprise value drivers.

* Design, build, test, and optimize scalable ETL/ELT pipelines in Databricks using Python, PySpark, SQL, notebooks, jobs, and pipeline orchestration patterns to support reliable Silver and Gold data products.

* Transform and model data from ERP and enterprise platforms, including Oracle Cloud, SAP, ADW, Microsoft Dataflow, Dataverse, and other approved data sources.

* Build and evaluate machine learning, statistical, and AI-assisted solutions where appropriate, including classification, forecasting, anomaly detection, text analytics, and natural language processing on structured and unstructured SCM data.

* Use Databricks platform capabilities such as notebooks, jobs, workflows, Unity Catalog, SQL warehouses, Genie Code, and Lakeflow/Lakeflow Designer where approved to accelerate development while maintaining enterprise standards.

* Maintain documentations, including idea assessments, requirements, design documents, and weekly status reports.

* Articulate technical knowledge, requirements, design and product details to internal business stakeholders in clear and plain language.

Skills and Qualifications

* Experience: 5-7 years of relevant SCM or product development experience.

o Advanced proficiency in data science, including statistical analysis, predictive analysis, text-based sentiment analysis, machine learning, and data visualization.

o Advanced proficiency in analyzing unstructured data such as PO line descriptions, customer feedbacks to extract insights

o Advanced proficiency in Python and PySpark in conjunction with Databricks for large-scale data processing.

o Hands-on knowledge with prompt engineering

o Hands-on experience in developing solutions using Microsoft Power Platform (Copilot Studio, Dataflow, Dataverse, Power Automate, and Model-driven Apps) for workflow automation and low-code development.

o In-depth knowledge of SAP and Oracle Cloud (SCM, A/P, Projects, Finance).

o Proficiency in SQL for data transformation is an asset.

o Experience with Alteryx for data preparation and workflow automation is an asset

* Industry Knowledge: Oil and gas sector, SCM Procure-to-Pay / Source-to-Pay processes and value drivers.

* Project Management: Skilled in agile/waterfall methodologies, stakeholder engagement, Project documentation (Power Point, Excel, Visio, etc)

* Education: Bachelor's degree in Commerce (SCM), Data Science, Engineering, or related field