Turbine Reliability Data Scientist — Predictive Analytics

Solaris Energy Infrastructure; Houston (TX); On-site; USD 85,000 - 125,000; Full time

Benefits offered by this job

Competitive compensation packages

Disability Insurance

Company paid Life and AD&D insurance

Company matching 401(k) retirement

Paid time off

Tuition Reimbursement

Job summary

Solaris Energy Infrastructure, Inc. is seeking a mid-level Data Analyst/Data Scientist to support turbine operations and engineering reliability efforts.

The role covers data engineering, ML modeling, and turbine domain knowledge to improve fleet reliability and provide operational and financial visibility. The ideal candidate will build dashboards for business stakeholders, develop predictive models for equipment health, and collaborate with engineering to validate outputs against OEM guidance.

Qualifications

• Bachelor's degree in Data Science, Statistics, Computer Science, Engineering, or related field (or equivalent experience).
• 2–5 years of experience in data analysis, preferably in industrial/energy/manufacturing operations.
• Proficiency in SQL and Python (pandas, scikit-learn, or similar).
• Experience building dashboards (Power BI, Tableau, or similar).
• Strong understanding of statistical analysis and predictive modeling techniques.
• Ability to communicate technical findings to non-technical stakeholders.
• Familiarity with time-series forecasting, anomaly detection, or condition-based monitoring techniques.
• Experience with SCADA/historian data (OSIsoft PI, or similar).
• Exposure to reliability engineering concepts (MTBF, RCM, FMEA).
• Experience with cloud data platforms (Azure, AWS) and ML deployment pipelines.

Responsibilities

• Build and maintain P&L dashboards tracking turbine fleet financial performance, availability, and cost drivers.
• Translate operational data into clear financial and operational KPIs for engineering and business leadership.
• Support monthly/quarterly reporting cycles with accurate, timely data.
• Collect, clean, and structure turbine downtime data from SCADA, CMMS, OEM reporting, and field logs.
• Classify and root-cause downtime events (mechanical, electrical, control system, weather, grid-related, etc.).
• Maintain a reliable, queryable historical database of outage and maintenance events across the fleet.
• Develop and deploy predictive models (ML-based and statistical) to forecast turbine downtime and component degradation ahead of failure.
• Build anomaly detection and early-warning tools using sensor/operational data (vibration, temperature, pressure, combustion parameters, etc.).
• Work with engineering to validate model outputs against physical failure modes and OEM guidance.
• Iterate on models as new failure data becomes available; track model performance over time.
• Partner with the Reliability Manager and engineering team to identify trends driving forced outages and derates.
• Support root cause analysis (RCA) efforts with data-driven insights.
• Recommend maintenance interval or strategy adjustments based on data trends (RCM/predictive maintenance support).
• Work closely with Operations, Engineering, and Asset Management to ensure data pipelines reflect real-world turbine conditions.
• Present findings to technical and non-technical stakeholders, including leadership.

Skills

SQL & Python

Dashboarding

Time-series forecasting

SCADA data

Reliability concepts

Cloud ML deployment

Communication skills

Education

Bachelor's in Data Science/Statistics/Engineering

Engineering background

Tools

Power BI

Tableau

Job description

Solaris Energy Infrastructure, Inc. is seeking a mid-level Data Analyst/Data Scientist to support turbine operations and engineering reliability efforts.

The role covers data engineering, ML modeling, and turbine domain knowledge to improve fleet reliability and provide operational and financial visibility. The ideal candidate will build dashboards for business stakeholders, develop predictive models for equipment health, and collaborate with engineering to validate outputs against OEM guidance.