Archived listing. The details below describe a past opening.
We are looking for a Data Scientist to help strengthen turbine reliability and improve operational visibility across a power generation fleet in Houston, Texas. This position combines hands-on data preparation, advanced analytics, and business reporting to turn complex equipment and performance data into practical insights for engineering and leadership teams. The ideal candidate can move comfortably between developing dashboards, analyzing downtime patterns, and creating predictive tools that support maintenance and performance decisions.
Responsibilities:
- Create and enhance dashboard reporting that highlights fleet financial results, equipment availability, and the primary factors affecting cost and performance.
- Convert operational and maintenance data into meaningful metrics and recurring reports for engineering teams, business partners, and leadership stakeholders.
- Gather, organize, and refine downtime, outage, and maintenance records from multiple operational sources and field documentation to support reliable analysis.
- Evaluate failure and outage events to identify root causes and categorize trends across mechanical, electrical, controls, weather, and grid-related issues.
- Build and maintain a dependable historical data set that supports querying, trend analysis, and long-term reliability reviews across the turbine fleet.
- Design and implement statistical and machine learning models that anticipate downtime risk, detect component deterioration, and support earlier intervention.
- Develop anomaly detection and early alert solutions using sensor and operating data such as vibration, temperature, pressure, and combustion-related measurements.
- Partner with reliability, operations, engineering, and asset management teams to validate analytical findings, improve data pipelines, and recommend maintenance strategy adjustments based on observed trends.
- Present technical conclusions and business implications clearly to both specialized and non-technical audiences, including management and leadership teams.
- Bachelor’s degree in Data Science, Statistics, Computer Science, Engineering, or a related discipline, or equivalent practical experience.
- 2–5 years of experience in data analysis or data science, preferably within industrial, manufacturing, energy, or other asset-intensive environments.
- Strong programming ability in Python, including experience with libraries such as pandas and scikit-learn.
- Experience building data workflows and ETL processes to prepare large operational data sets for analysis and reporting.
- Proficiency with dashboard and visualization tools such as Power BI, Tableau, or comparable platforms.
- Solid foundation in statistical methods, predictive modeling, time-series analysis, and anomaly detection techniques.
- Familiarity with SCADA or historian data environments, along with exposure to reliability engineering concepts and condition-based monitoring approaches.
- Experience working with modern data platforms such as Snowflake, Azure Databricks, or similar cloud-based analytics environments.