Lead Fleet Reliability Data Engineer

Job Description Summary

We are seeking a Fleet Reliability Data Engineer to join the Fleet Performance & Analytics team within the Fleet Intelligence & Reliability organization. This role will build and maintain the trusted data foundation required to understand the health, performance, reliability, and intervention history of GE Vernova's global Solar and Storage installed fleet.
The engineer will connect operational telemetry, alarms and events, asset hierarchy, equipment configuration, software versions, maintenance activities, component replacements, field interventions, failure records, and Root Cause Analysis findings into reliable and scalable engineering datasets. The role will ensure that fleet data is complete, contextualized, traceable, and accessible for reliability analysis, performance monitoring, technical investigations, and predictive analytics.
This role is distinct from a traditional enterprise data-engineering position. It requires strong data-engineering capability combined with an understanding of industrial assets, reliability concepts, and engineering workflows. The successful candidate will partner closely with Reliability & RCA, Data Analytics & AI, Product Engineering, Controls, Digital Technology, Quality, and Field Operations to convert fragmented fleet information into durable engineering intelligence.

Job Description

Roles and Responsibilities

• Design, build, and maintain scalable data pipelines that ingest and integrate operational telemetry, alarms, events, maintenance records, field interventions, asset configuration, software versions, and engineering findings.
• Develop and maintain a standardized fleet asset model and hierarchy covering sites, systems, equipment, assemblies, components, serial numbers, configurations, and relevant parent-child relationships.
• Establish traceability for significant interventions, component replacements, repairs, configuration changes, software updates, and other lifecycle events affecting critical fleet equipment.
• Create curated and reusable reliability datasets that support Root Cause Analysis, failure trending, recurrence analysis, fleet exposure assessment, performance monitoring, and corrective-action validation.
• Develop robust methods to link operational events and alarms with maintenance actions, failure records, product configuration, environmental conditions, and investigation outcomes.
• Define and implement data-quality rules for completeness, accuracy, consistency, timeliness, uniqueness, lineage, and contextual integrity.
• Build automated controls that identify missing data, inconsistent asset identifiers, invalid timestamps, duplicate interventions, configuration conflicts, and broken data relationships.
• Partner with Reliability & RCA engineers to structure investigation data, identify comparable fleet events, define affected populations, and preserve reusable evidence from completed RCAs.
• Partner with Data Analytics & AI engineers to provide governed, documented, and analysis-ready data products for dashboards, anomaly detection, predictive models, and engineering decision-support tools.
• Develop fleet master-data standards, naming conventions, taxonomies, failure classifications, intervention categories, and metadata required for consistent fleet-level analysis.
• Integrate data from industrial historians, SCADA systems, remote-monitoring platforms, service-management systems, engineering databases, and other relevant sources.
• Create reliable APIs, data services, semantic layers, and governed access patterns that enable engineering teams to use fleet data efficiently and consistently.
• Maintain data lineage, source-to-target mappings, interface specifications, transformation logic, ownership definitions, and technical documentation for reliability data products.
• Implement monitoring and alerting for data-pipeline health, ingestion failures, schema changes, latency, processing errors, and data-quality degradation.
• Support migration and harmonization of historical fleet data while preserving source context, auditability, and engineering meaning.
• Work with cybersecurity, data-governance, and platform teams to ensure appropriate access control, retention, privacy, backup, recovery, and lifecycle management.
• Improve engineering productivity by automating repetitive data preparation, reconciliation, event correlation, fleet-population analysis, and reliability reporting activities.
• Communicate data limitations, quality risks, dependencies, and remediation priorities clearly to engineering and leadership stakeholders.
• Promote a culture of data ownership, traceability, technical rigor, collaboration, and continuous improvement across the Fleet Intelligence & Reliability organization.

Required Qualifications

• Bachelor's degree in Computer Science, Data Engineering, Software Engineering, Electrical Engineering, Systems Engineering, Control Systems Engineering, or a related technical field.
• Minimum of 8 years of experience in data engineering, industrial data systems, software engineering, reliability data, operational technology data, or a related technical function.
• Strong proficiency in SQL and Python for data ingestion, transformation, validation, automation, testing, and data-product development.
• Experience designing and operating ETL or ELT pipelines that integrate data from multiple structured, semi-structured, and time-series sources.
• Experience with data modeling, relational databases, schemas, APIs, version control, automated testing, and production-support practices.
• Experience implementing data-quality validation, lineage, monitoring, error handling, reconciliation, and traceability controls.
• Ability to translate engineering and reliability requirements into scalable data structures, interfaces, and reusable data products.
• Strong written and verbal communication skills in English and the ability to collaborate across global engineering, digital, and operational teams.

Desired Characteristics

• Advanced degree in Data Engineering, Computer Science, Engineering, Reliability, or a related discipline.
• Experience with renewable energy, solar inverters, battery energy storage systems, power electronics, plant controls, power generation, or industrial automation.
• Understanding of reliability engineering concepts, including failure modes, recurrence, affected population, corrective actions, availability, maintainability, and Root Cause Analysis.
• Experience working with industrial time-series data, alarms, events, maintenance history, asset configuration, and equipment lifecycle records.
• Experience with cloud data platforms, data lakes or lakehouses, distributed processing, workflow orchestration, and streaming or near-real-time ingestion.
• Experience with technologies such as Spark, Databricks, Snowflake, Azure, AWS, Google Cloud, Airflow, dbt, Kafka, or equivalent platforms.
• Familiarity with SCADA systems, industrial historians, OPC-UA, Modbus, IEC protocols, and remote-monitoring architectures.
• Experience developing asset models, knowledge graphs, semantic layers, metadata catalogs, master-data solutions, or industrial digital twins.
• Knowledge of service-management, maintenance-management, product-lifecycle, or enterprise asset-management data structures.
• Experience with DevOps or DataOps practices, including CI/CD, infrastructure as code, containerization, automated testing, observability, and controlled deployment.
• Knowledge of cybersecurity and data-governance requirements applicable to industrial and operational technology environments.
• Experience supporting analytics, machine-learning, condition-monitoring, or predictive-maintenance solutions with production-quality data products.
• Ability to understand engineering drawings, equipment structures, configuration records, failure reports, and technical investigation documentation.
• Strong systems thinking, attention to detail, ownership of data quality, and ability to resolve ambiguous or conflicting source information.
• Self-starting attitude with the ability to prioritize foundational work, collaborate across functions, and deliver sustainable solutions rather than one-time data extracts.

Additional Information