Senior Systems Engineer - Predictive Fleet Intelligence

The Senior Systems Engineer - Predictive Fleet Intelligence is the engineering authority responsible for defining how fleet health is monitored, how developing equipment failures are detected, and how engineering knowledge is transformed into scalable digital solutions.

Serving as the domain expert for predictive fleet intelligence, this role establishes the engineering requirements, monitoring strategies, detection logic, alerting philosophy, and technical specifications that enable Software Engineering and Data Science teams to develop predictive monitoring applications, fleet intelligence products, and operational decision-support tools.

Rather than developing software or analytics models directly, this engineer defines what should be monitored, why it matters, how abnormal behavior should be identified, and what actions should result. Success is measured by reducing unplanned downtime, improving fleet reliability, increasing early fault detection, and continuously expanding the organization's predictive engineering capabilities.

Working across Engineering, Reliability, Operations, Controls, Technical Services, Digital Solutions, and Data Science, this role transforms operational experience, root cause investigations, and equipment expertise into reusable engineering standards that improve the performance of an entire fleet of industrial assets.

This role is responsible for developing and continuously improving the engineering products that enable predictive fleet intelligence, including:

• Fleet Health Monitoring Specifications defining monitoring objectives, required data sources, operating thresholds, engineering logic, and alert behavior.

• Predictive Detection Rule Specifications that enable Software Engineering and Data Science teams to develop automated monitoring applications and predictive analytics.

• Failure Pattern & Leading Indicator Rules Library documenting confirmed failure signatures, detection criteria, engineering rationale, probable causes, and recommended operational responses.

• Predictive Alert Specifications defining alert context, response guidance, escalation logic, notification strategies, and acceptance criteria.

• Fleet Health Dashboard & Operational Intelligence Specifications defining the engineering requirements for dashboards, reports, and digital decision-support products.

• Standardized Alert Response Packages enabling field operations and technical support teams to investigate and resolve predictive alerts without requiring engineering involvement.

• Alert Effectiveness Reports & Continuous Improvement Recommendations measuring monitoring performance, operational outcomes, false-positive trends, and opportunities to improve predictive monitoring capabilities.

• Define the engineering strategy for monitoring the health and performance of complex industrial assets, including control systems, power systems, mechanical equipment, supporting infrastructure, communications networks, and deployed software configurations.

• Author detailed monitoring requirements that define what equipment should be monitored, what operating conditions represent normal performance, and what deviations indicate degradation or impending failure.

• Establish system health logic, engineering thresholds, operating limits, and classification criteria that distinguish healthy operation from abnormal conditions.

• Define data acquisition requirements by identifying the signals, parameters, instrumentation, and operational data necessary to support meaningful equipment health assessment.

• Develop engineering specifications for predictive monitoring capabilities, documenting leading indicators, failure signatures, and detection logic that enable early identification of developing equipment failures.

• Develop equipment-specific monitoring standards and predictive detection strategies for major asset classes across the fleet, defining how healthy operation, degradation, and impending failure manifest within operational data.

• Define leading indicators and engineering detection criteria that enable developing equipment failures to be identified sufficiently in advance to support proactive operational intervention.

• Define monitoring strategies for software version compliance and control system configuration management to ensure fleet-wide operational consistency.

• Continuously improve alarm rationalization and monitoring strategies to ensure operators receive timely, actionable information while minimizing nuisance notifications.

• Author engineering specifications that Software Engineering and Data Science teams use to develop fleet-wide monitoring capabilities.

• Translate confirmed root cause investigations, reliability analyses, operational learning, and equipment performance trends into predictive monitoring strategies that prevent recurrence of failures.

• Build and maintain the engineering knowledge base of confirmed failure modes, leading indicators, detection thresholds, probable causes, engineering assumptions, and recommended field responses.

• Analyze fleet performance, equipment downtime, and operational events to identify recurring failure mechanisms and prioritize opportunities for predictive monitoring.

• Develop engineering approaches for time-series analysis that characterize how degradation develops over time across major equipment systems.

• Author detection rule specifications that define how abnormal operating behavior should be identified while partnering with Data Science teams to translate those specifications into predictive analytics applications.

• Continuously expand predictive monitoring coverage across fleet systems by identifying new opportunities to detect failures earlier and improve operational reliability.

• Establish governance processes that ensure confirmed root cause investigations, operational lessons learned, and reliability improvements are systematically incorporated into the organization's monitoring standards, detection rules, and engineering knowledge base.

• Continuously improve the Rules Library by validating existing detection logic against operational outcomes and incorporating new failure signatures as they are discovered across the fleet.

• Define the engineering specifications for predictive alerts, ensuring every alert provides sufficient operational context-including supporting trend information, probable causes, recommended response actions, and expected operational outcomes-to enable informed decision-making rather than simply notifying users of abnormal conditions.

• Design alert thresholds and notification strategies that maximize actionable early warning while minimizing false positives and operational fatigue.

• Define escalation architectures that ensure the appropriate personnel receive the right information at the right time based on severity, operational risk, and business impact.

• Lead the deployment of new predictive monitoring capabilities by developing communication plans, response guidance, and training materials that enable Operations, Maintenance, and Technical Support teams to confidently interpret and respond to predictive alerts.

• Develop and maintain engineering metrics that measure alert effectiveness, intervention success, operational outcomes, and monitoring system performance.

• Conduct systematic reviews of monitoring effectiveness, refining detection logic, thresholds, and alert strategies based on operational feedback and measured results.

• Define the engineering specifications for fleet health dashboards, operational bulletins, and decision-support products that provide field operations and technical support with structured visibility into equipment condition, emerging risks, and fleet-wide reliability trends.

• Define the engineering specifications for standardized fleet health reporting products-including operational summaries, recurring trend reports, and fleet reliability analyses-that enable proactive maintenance planning and operational decision-making.

• Design standardized alert response packages that provide field personnel and remote support teams with the technical information, historical context, probable causes, recommended first-response actions, and expected resolution criteria necessary to resolve predictive alerts without requiring engineering intervention.

• Partner with Digital Solutions teams to deliver fleet intelligence through enterprise dashboards, mobile applications, and other digital platforms.

• Establish engineering standards, governance processes, and best practices that enable scalable, repeatable fleet health monitoring across the organization.

• Bachelor's degree in Mechanical Engineering, Electrical Engineering, Controls Engineering, Systems Engineering, Petroleum Engineering, or a related engineering discipline.

• Eight (8) or more years of experience in systems engineering, reliability engineering, industrial controls, automation, predictive maintenance, asset performance management, or complex industrial systems.

• Experience working with large-scale industrial equipment in asset-intensive industries such as drilling, mining, heavy equipment, manufacturing, marine, rail, power generation, or similar environments.

• Strong understanding of industrial control systems, instrumentation, condition monitoring technologies, and operational data platforms.

• Experience working with industrial historians, SCADA systems, PLC-based equipment, or time-series operational data.

• Working knowledge of Root Cause Analysis (RCA), Failure Modes and Effects Analysis (FMEA), reliability engineering, and predictive maintenance methodologies.

• Demonstrated experience developing engineering standards, technical specifications, system requirements, monitoring strategies, or equipment health frameworks.

• Experience collaborating with software engineering, digital product, or data science teams to deliver industrial monitoring or predictive analytics solutions.

• Experience designing predictive maintenance or condition monitoring programs for complex industrial assets.

• Familiarity with machine learning, industrial analytics, digital twins, or asset performance management platforms.

• Knowledge of industrial networking, automation platforms, fleet management systems, and equipment health monitoring technologies.

• Experience defining engineering requirements for digital products or enterprise monitoring systems.

• Strong technical writing, analytical reasoning, and systems thinking skills.

• Excellent communication and stakeholder management abilities with experience influencing cross-functional engineering organizations.

Additional Details:

This position requires the person to be able to work in a time sensitive, high visibility role and regularly travel as needed to support business units and to visit work sites. It may also require extended travel to remote locations and/or overnight stay(s) during variable hours. Variable work hours include hours worked on the weekend, on holidays, and hours to travel within and outside of the assigned region. The Engineer must work with an emphasis on planning, multitasking, and prioritization to maximize efficiency of the team. Must be able to work closely with others and manage customer interaction in a professional manner. Ability to safely navigate work sites with occasional walking, climbing, standing, stepping, working at heights, etc., during normal operating conditions (day/night, outdoor hot/cold weather) and while utilizing designated personal protective equipment (PPE).