Data Scientist, Reliability Engineering

CyrusOne is a leading company in data center services, and they are seeking a Data Scientist for Reliability Engineering. This role is responsible for developing analytics and models to improve reliability outcomes in mission-critical systems, partnering with engineering teams to transform data into actionable insights.

Responsibilities:

• Build statistical and machine‑learning models that detect degradation, anomalies, and failure precursors in mission‑critical infrastructure data
• Apply reliability‑relevant methods (e.g., time series analysis, survival/MTTF modeling, probabilistic risk signals, forecasting) to quantify failure likelihood and uncertainty
• Develop repeatable analytical frameworks to support Reliability Engineering workflows (e.g., maintenance strategy effectiveness, spares exposure, recurring failure patterns)
• Design and maintain data pipelines that integrate CMMS/work management, BMS/EPMS telemetry, condition-monitoring outputs, and incident/RCA artifacts
• Establish data quality standards, validation checks, and documentation to improve trust, repeatability, and scalability of reliability analytics
• Partner with platform/IT stakeholders to ensure analytics solutions are secure, supportable, and fit-for-scale
• Translate analytical findings into clear insights and recommendations that Reliability Engineers and leaders can act on (risk reduction, maintenance optimization, capital planning support)
• Build and maintain dashboards, scorecards, and leading indicators that enable portfolio-level visibility into degradation trends and reliability risk
• Support post-incident learning by structuring data for RCA/FMEA and identifying latent/systemic patterns across events
• Deliver analytics as reusable “products” (models, pipelines, dashboards, playbooks) with defined inputs/outputs, monitoring, and change control
• Educate stakeholders on interpretation, limitations, and uncertainty to enable responsible use of predictive/diagnostic outputs

Requirements:

• Bachelor's degree in Data Science, Statistics, Applied Math, Engineering, Computer Science, or similar quantitative field
• 4+ years (mid-level) or 6+ years (senior-level) of applied analytics/data science experience in operational, industrial, infrastructure, or high-availability environments
• Proficiency in Python for data analysis/modeling and SQL for data extraction/joins across relational datasets
• Demonstrated ability to work with noisy, imperfect operational datasets and produce reliable, explainable insights
• Strong communication skills: able to explain models and results to engineering and operations audiences
• Experience with CMMS/work management data, BMS/EPMS telemetry, historian/time-series data, or condition monitoring programs
• Experience applying analytics to reliability, maintenance optimization, asset management, anomaly detection, or operational risk
• Familiarity with reliability methods and terms (RCM, FMEA, RCA, asset criticality) — deep engineering expertise not required but must collaborate effectively with SMEs