Operate or control petroleum refining or processing units. May specialize in controlling manifold and pumping systems, gauging or testing oil in storage tanks, or regulating the flow of oil into pipelines.
U.S. Workers
34,860
Median Salary
$97,540
10-Year Growth
-2.8%
Annual Openings
3,200
Typical entry: High school diploma or equivalent
24 of 24 tasks have some AI capability
Exposure Trend
This score reflects estimated AI technical capability for tasks in this occupation. It does not predict employment changes, and it does not account for company-specific constraints, regulation, or adoption barriers.
Monitor process indicators, instruments, gauges, and meters to detect and report any possible problems.
AI: Fully automatable - Monitoring instruments and detecting/reporting anomalies is a core AI/analytics capability that can be fully automated with existing sensor and software technology.
Start pumps and open valves or use automated equipment to regulate the flow of oil in pipelines and into and out of tanks.
AI: Fully automatable - Starting pumps and operating motorized valves or automated regulators is already routinely performed by supervisory control systems and can be fully automated by AI orchestration.
Control or operate manifold and pumping systems to circulate liquids through a petroleum refinery.
AI: Fully automatable - Controlling manifolds and pumping systems in refineries is a well‑instrumented process that advanced control systems and AI can operate end‑to‑end under normal conditions.
Operate control panels to coordinate and regulate process variables such as temperature and pressure, and to direct product flow rate, according to process schedules.
AI: Fully automatable - Coordinating process variables via control panels according to schedules is exactly what modern DCS, APC, and AI process optimization systems are designed to do and can fully automate.
Verify that incoming and outgoing products are moving through the correct meters, and that meters are working properly.
AI: Fully automatable - Verifying flow and meter health is primarily a data/telemetry task that analytics and automated diagnostics can reliably perform.
Read automatic gauges at specified intervals to determine the flow rate of oil into or from tanks, and the amount of oil in tanks.
AI: Fully automatable - Reading automatic gauges at intervals is fully automatable via SCADA/telemetry systems and software monitoring.
Plan movement of products through lines to processing, storage, and shipping units, using knowledge of system interconnections and capacities.
AI: Fully automatable - Planning product movements through networks is an optimization problem that AI and schedulers can fully automate given accurate system models and constraints.
Read and analyze specifications, schedules, logs, test results, and laboratory recommendations to determine how to set equipment controls to produce the required qualities and quantities of products.
AI: Fully automatable - AI and model‑based control can analyze specs, logs, and lab results to determine and set equipment controls to meet quality and quantity targets.
Record and compile operating data, instrument readings, documentation, and results of laboratory analyses.
AI: Fully automatable - Recording and compiling instrument and laboratory data is a routine data‑handling task that can be fully automated.
Perform tests to check the qualities and grades of products, such as assessing levels of bottom sediment, water, and foreign materials in oil samples, using centrifugal testers.
AI: Fully automatable - Chemical/centrifuge testing workflows are widely instrumented and can be run and interpreted by automated laboratory systems and AI, enabling full automation of these tests in many settings.
Prepare calculations for receipts and deliveries of oil and oil products.
AI: Fully automatable - Preparing receipts and delivery calculations is a deterministic, data-driven task that can be fully automated with software and AI accounting/logistics systems.
Clean interiors of processing units by circulating chemicals and solvents within units.
AI: Fully automatable - Circulating cleaning chemicals within units is typically controlled by process control systems and can be fully automated and supervised by AI in modern plants.
Calculate test result values, using standard formulas.
AI: Fully automatable - Calculating test results using standard formulas is purely computational and can be fully automated by software or AI.
Signal other workers by telephone or radio to operate pumps, open and close valves, and check temperatures.
AI: Partial - AI can automatically send telephone/radio messages and alerts, but safety-critical signaling in dynamic field situations typically requires human confirmation and oversight.
Operate auxiliary equipment and control multiple processing units during distilling or treating operations, moving controls that regulate valves, pumps, compressors, and auxiliary equipment.
AI: Partial - Distributed control systems and advanced controllers can manage routine valve/pump/compressor operations, but full autonomous operation across complex, abnormal conditions still requires human operator judgment.
Coordinate shutdowns and major projects.
AI: Partial - AI tools can plan, schedule, and coordinate many aspects of shutdowns and projects, but high-stakes decision-making, cross-stakeholder negotiation, and legal/safety accountability keep human oversight necessary in 2025.
Synchronize activities with other pumphouses to ensure a continuous flow of products and a minimum of contamination between products.
AI: Partial - Routine synchronization between pumphouses can be automated, but preventing contamination and handling cross-site exceptions typically needs human coordination and verification.
Patrol units to monitor the amount of oil in storage tanks, and to verify that activities and operations are safe, efficient, and in compliance with regulations.
AI: Partial - Remote sensors, cameras, and analytics can perform much of the monitoring, but physical patrols and complex safety/compliance judgments remain partially human-dependent.
Maintain and repair equipment, or report malfunctioning equipment to supervisors so that repairs can be scheduled.
AI: Partial - AI can detect faults, diagnose issues, and schedule or recommend repairs, but actual maintenance and hands‑on repairs require human technicians.
Collect product samples by turning bleeder valves, or by lowering containers into tanks to obtain oil samples.
AI: Partial - Collecting physical oil samples requires manual access and dexterous manipulation; while remote samplers and robots exist, they are not universally deployed so the task is only partially automatable in 2025.
Lower thermometers into tanks to obtain temperature readings.
AI: Partial - Tank temperature measurement can be fully automated where sensors are installed, but the described manual lowering of thermometers still requires physical action in many facilities, so automation is partial.
Inspect pipelines, tightening connections and lubricating valves as necessary.
AI: Partial - Inspection can be largely automated with sensors and vision systems, but tightening connections and lubricating valves still typically require human or specialized robotic intervention, so the task is only partially automatable.
Clamp seals around valves to secure tanks.
AI: Partial - Clamping seals around valves is a manual, physical task that can be automated with robotics in some contexts but remains largely manual across the industry as of 2025.
Conduct general housekeeping of units, including wiping up oil spills and performing general cleaning duties.
AI: Partial - General industrial cleaning and spill response can be assisted by automation and specialized equipment, but varied environments and complex manual cleanup steps limit full automation today.