Data Scientist

The Data Scientist role at PROPWR supports power generation operations through advanced analytics, predictive modeling, and actionable insights. The position focuses on analyzing operational data from power generation assets, SCADA systems, and condition monitoring platforms to improve performance, reliability, and operational efficiency in Houston, TX (onsite).

• Analyze large datasets from power generation assets, SCADA systems, sensors, and historian platforms.
• Identify trends, anomalies, and performance deviations affecting asset reliability and availability.
• Validate and improve data quality across operational systems and data pipelines.
• Develop predictive models for equipment health, failure probability, and maintenance planning.
• Build forecasting models for generation output, performance, and reliability.
• Provide data-driven insights to support reliability engineering, including failure mechanisms and asset risk.
• Conduct hypothesis testing and statistical analysis to validate assumptions and inform engineering decisions.
• Create dashboards, KPIs, and performance reporting tools for engineering and operations teams.
• Communicate complex analytical findings into clear, actionable recommendations for non-technical stakeholders.
• Collaborate with Operations, Maintenance, and Engineering to implement operational improvements based on insights.
• Support root cause analysis (RCA) investigations with data-driven evidence and modeling.
• Partner with reliability engineers to integrate predictive analytics into maintenance strategies.
• Document models, assumptions, methodologies, and business impact.
• Maintain version control, code quality, and reproducibility standards.
• Support deployment of models into production environments when applicable.
• Stay current with emerging analytics tools, machine learning techniques, and power-generation technologies.
• Maintain compliance with Health, Safety, and Environment (HSE) policies by completing required HSE training sessions and safety meetings, and by using proper Personal Protective Equipment (PPE).

• Bachelor’s degree in Data Science, Engineering, Mathematics, Statistics, Computer Science, or a related field.
• 3–7 years of experience in data science, analytics, or applied machine learning.
• Strong experience with Python or R and SQL
  .
• Statistical modeling and machine learning techniques.
• Time series data analysis.
• Experience working with operational or industrial datasets.
• Ability to communicate complex analytical concepts clearly and effectively.

• Experience in power generation, energy, utilities, or industrial operations.
• Familiarity with SCADA, plant historian data, or condition monitoring systems.
• Experience with asset performance analytics or maintenance optimization.
• Knowledge of turbines, generators, reciprocating engines, or other industrial equipment.
• Experience deploying models into production environments.
• Exposure to reliability engineering concepts such as RCM, FMEA, and RCA.

• Python
• R
• SQL

• Regularly required to sit, stand, or walk; use hands to manipulate, handle, or feel; reach with hands and arms; stoop or bend; and talk or hear.
• Occasionally lift and/or move up to 20 lbs
  .
• Reasonable accommodation may be made for individuals with disabilities to perform major responsibilities.

• Noise level in some work environments can be moderate.
• May encounter extreme weather conditions while performing major duties.
• Reasonable accommodation may be provided for individuals with disabilities to perform major responsibilities.

The information provided in this job description indicates the general nature and level of work performed by employees within the role’s classification. This job description is not intended to be a comprehensive inventory of all duties, responsibilities, or qualifications required of employees assigned to this role.