Qura

About

Qura is a mechanical maintenance and reliability engineer whose career has been spent where equipment actually runs — pump rooms, compressor skids, workshops, and plant turnarounds across the oil and gas industry. Born in Egypt, he built his career in Oman and the United Arab Emirates and is now based in Australia, where he works as a Projects and Proposals Engineer at National Oilwell Varco (NOV), leading complex projects and proposals with a focus on quality assurance and equipment reliability.

Before NOV, Qura spent six years at TAQA in Oman. As a Maintenance Engineer he reduced equipment downtime from three months to one week, ran the annual optimisation of the company's CMMS, planned maintenance in SAP Plant Maintenance, and scheduled inspections including pressure testing, magnetic particle inspection, and ultrasonic wall-thickness testing. Promoted to Workshop Supervisor, he refined maintenance procedures for all rotary equipment — cutting equipment failure rates by 5% in 2023 — engineered the selection and commissioning of ten multi-stage pumps from scope of works through site acceptance testing, delivered four new projects in a single year, led the rotary maintenance team through a critical four-day plant turnaround, and represented rotary equipment in HAZOP meetings with clients including PDO, Shell, and Oxy.

Earlier roles grounded that work in the fundamentals: maintaining pumps, compressors, and piping hook-ups at Petrogulf in Egypt, and designing and installing pumping and firefighting systems, screw compressors, and centrifugal pump overhauls with Alhoqani in Oman.

Alongside a decade of field practice, Qura has built a parallel track in artificial intelligence. He holds a Bachelor of Engineering in Mechanical Engineering from Benha University and an MSc in Artificial Intelligence from the University of Essex, and is completing an MS in Computer Science at the Georgia Institute of Technology. He is CMRP certified, an ASQ Certified Reliability Engineer, a Project Management Professional, and a certified Quality Management System Lead Auditor — and works in English, Arabic, and German.

Domain Expertise

• Rotating equipment maintenance — pumps, compressors, and multi-stage pump systems, from overhaul to selection, commissioning, and site acceptance testing
• Reliability engineering — failure-rate reduction, maintenance procedure design, and reliability-centred decision-making across equipment fleets
• CMMS and SAP Plant Maintenance — maintenance planning, system optimisation, and the data discipline that makes reliability metrics trustworthy
• Inspection and integrity — pressure testing, magnetic particle inspection, and ultrasonic wall-thickness programmes for oil and gas equipment
• Turnarounds and process safety — leading rotary maintenance through plant turnarounds and HAZOP reviews with major operators
• QA/QC and documentation — scope-of-works libraries, QA/QC document control, checklists, and work instructions
• Applied AI and machine learning — predictive maintenance, predictive modelling, and Industry 4.0 techniques for asset reliability

Publications

• A Systematic Approach to Reducing Human Errors in Maintenance Processes Using Multi-Agents
• Predictive Maintenance Automation: Artificial Maintenance Management Agent (AMMA) Framework

Both papers address the same question from different directions: how multi-agent AI can take on the repetitive, error-prone parts of maintenance management — and how a maintenance agent can move a team from reactive work to predictive maintenance.

The Problem Maintenance Software Has Not Solved

Qura's view of maintenance software comes from years of using it on the job. A CMMS records what happened. It rarely helps anyone understand why. The certificate for a pressure test sits in one place, the job card for the repair in another, the spare-parts history in a third — and the reasoning that connects them lives in the head of whichever engineer has looked after that equipment longest.

That knowledge is exactly what disappears during a shift change, a rotation, or a resignation. A junior engineer facing a repeat pump failure can see the work orders but not the pattern behind them. A supervisor preparing for mobilisation has to chase certificates by hand. The data exists; the judgment that makes it useful does not travel with it.

His aim is not the theory of Industry 4.0 but its practice: applying AI and machine learning to real maintenance records so that predictive maintenance and asset reliability become something a maintenance team can rely on — with every answer traceable to the records behind it.

Collaboration with Praxa

Qura is the domain expert and co-author behind RelyentX, Praxa's AI-native enterprise asset management and CMMS platform for oil and gas. The question that drives it is his: what if you had a maintenance assistant who works for you 24/7 and knows the answer to every question about your equipment?

RelyentX's design follows the way he works. The equipment taxonomy mirrors how a reliability engineer structures a fleet. The inspection disciplines are the ones he scheduled at TAQA. Reliability metrics are rebuilt from job cards and failures, so they can be checked rather than trusted. And the AI copilot answers questions from a company's own records — showing the sources behind every answer, and taking no action without approval.

For more on why Praxa structures product development around domain practitioners rather than data, read: Why domain expertise is the missing ingredient in AI product development.