ENGINEERING EXPERIENCE. A DATA-DRIVEN FUTURE.

Real-world
operations.
Reliable data.
Practical AI.

I’m Abdulrahman Alzahrani.
A data engineering lead connecting hands-on operations, analytics and business-focused problem-solving, with a focus on Saudi Arabia’s digital future.

Explore my work Meet the person behind the CV

AL KHOBAR, SAUDI ARABIAENERGY · DATA · BUSINESS

Abstract geological layers transforming into luminous structured data traces

FIELD EXPERIENCEDATA INTELLIGENCE

FIELD / DATA

Understand the operation.
Then improve the system.

7+ yearsEngineering & operational experience

Halliburton2019–present · Field & Digital Center

MSc Artificial IntelligenceUniversity of Leeds · In progress

01 THE THROUGH-LINE

Good technology starts
with understanding
the real problem.

My career began where the data is created: in the field.

As a wireline field engineer, I learned to make decisions under pressure, work closely with clients and understand what reliable operational delivery really takes.

In Halliburton’s Digital Center, that perspective became a foundation for leading data quality and delivery work. Today, I’m building on it through an MSc in Artificial Intelligence, connecting technical methods with problems that matter to the people using them.

I’m building on my experience in operations and data through my studies in AI, bringing together an understanding of how work gets done and how technology can improve it. This path aligns with the Kingdom’s direction toward a knowledge- and innovation-driven economy under Saudi Vision 2030.

Operations gave me context.
Data gave me a different way to improve it.

01 / OPERATIONS

Close to the work.

Wireline field engineering, client coordination and delivery in demanding environments.

02 / DATA LEADERSHIP

Trust in the data.

Well-log data preparation, quality control and digital delivery, alongside team coordination.

03 / APPLIED AI

Build on the foundation.

Postgraduate study and academic projects in machine learning and data analysis.

02 SELECTED WORK

A closer look at
how I work.

Professional experience and applied projects.
Different settings. The same practical mindset.

PROFESSIONAL EXPERIENCE

Data quality at the operational edge

Digital well-log preparation, validation and delivery

CONTEXT

Operational datasets need to be dependable before they can support analysis or decisions. My field background helps me understand what the data represents, as well as how it is processed.

MY CONTRIBUTION

Lead a data-engineering team working on digital well-log datasets.
Support extraction, cleaning and validation of well-log datasets.
Work across teams on depth matching, environmental corrections and delivery requirements.
Support team capability through onboarding and training.

THE CONNECTION

Domain understanding makes technical quality checks more meaningful.

AI BRIDGE · THE DOCK, DUBLIN

AI-powered financial learning

From problem framing to a personalized audio-learning concept

THE CONCEPT

Developed a financial-education concept in a four-person team during MCIT’s AI Bridge program, including two weeks at Accenture’s The Dock in Dublin. The proposed app would turn a user’s financial goals and interests into short, personalized AI-generated podcasts, with progress tracking and gamification.

We worked with consultants to structure the problem, define who it mattered to and connect the idea to a clear user need.

MY CONTRIBUTION

Researched the problem and framed hypotheses, applying techniques from McKinsey Forward.
Developed personas and mapped the user journey, using ChatGPT for scenario exploration.
Contributed to the concept, success measures, business model and proposed roadmap.
Helped combine the team’s strongest ideas and presented our recommendations to partners in Dublin and Saudi Arabia.

MCIT AI Bridge · Team concept project at Accenture’s The Dock

THE CONNECTION

Turning an open-ended problem into a clear user journey, a business proposition and a practical next step.

ACADEMIC PROJECT

Energy Efficiency

Bayesian regression and neural networks for an energy problem

PROJECT FOCUS

Compared Bayesian linear regression and a multilayer neural network to predict cooling load from eight design features across 768 simulated building configurations. Built with Python, pandas and scikit-learn.

Used preprocessing pipelines, five-fold cross-validation and hyperparameter tuning, then evaluated both models on the same 154 held-out observations.

RESULTS AND INTERPRETATION

The neural network achieved a test mean absolute error of 0.84, compared with 2.09 for Bayesian regression. I examined generalization gaps and convergence warnings, and connected prediction errors to cooling-system sizing and equipment costs.

University of Leeds · Academic project · October 2026
Simulation-based results, not a deployed system. Performance on measured buildings and unfamiliar designs requires further validation.

THE CONNECTION

Choosing a model means weighing accuracy, limitations and the decision it will support.

ACADEMIC PROJECT

Insurance fraud classification

Applied machine learning for a classification problem

PROJECT FOCUS

Prepared and explored insurance data, engineered features and compared logistic regression with random forest classification.

WHAT IT DEMONSTRATES

Evaluated models with cross-validation, precision, recall and F1, considering the business costs of different errors. Built with Python, pandas and scikit-learn.

University of Leeds · Academic project · 2026

THE CONNECTION

A model needs an explanation as well as a prediction.

ACADEMIC PROJECT

University rankings analysis

Exploring data, patterns and the questions behind a ranking

PROJECT FOCUS

Cleaned university-ranking data, handled missing values and used visual comparisons to investigate trends and correlations.

WHAT IT DEMONSTRATES

Interpreted findings alongside the limitations of the dataset. Built with Python, pandas, Matplotlib and Seaborn.

THE CONNECTION

Useful analysis helps people understand what a number means.

03 WHERE I ADD VALUE

Three perspectives.
One connected approach.

Explore the experience I bring to a team.

Make the data dependable.

Experience with data extraction, cleaning, validation and digital well-log delivery. I connect data quality requirements with the operational context behind them.

Data qualityValidationWell-log processingCross-team delivery

04 ALWAYS BUILDING

Engineering roots.
Continuing to grow.

IN PROGRESS

MSc Artificial Intelligence

University of Leeds

DEGREE

BSc Electrical Engineering

California State University, Fresno

PROFESSIONAL DEVELOPMENT

Leadership Principles & CORe

Harvard Business School Online

TECHNICAL FOUNDATION

Data Science Immersive

General Assembly

05 START A CONVERSATION

Let’s turn experience
into what’s next.

For opportunities connecting data, AI, operations and business improvement.

appdulrahman@gmail.com

Get in touch LinkedIn

Real-worldoperations.Reliable data.Practical AI.

Good technology startswith understandingthe real problem.

Close to the work.

Trust in the data.

Build on the foundation.

A closer look athow I work.

Data quality at the operational edge

AI-powered financial learning

Energy Efficiency

Insurance fraud classification

University rankings analysis

Three perspectives.One connected approach.

Make the data dependable.

Engineering roots.Continuing to grow.

MSc Artificial Intelligence

BSc Electrical Engineering

Leadership Principles & CORe

Data Science Immersive

Let’s turn experienceinto what’s next.

Real-world
operations.
Reliable data.
Practical AI.

Good technology starts
with understanding
the real problem.

A closer look at
how I work.

Three perspectives.
One connected approach.

Engineering roots.
Continuing to grow.

Let’s turn experience
into what’s next.