Data Scientist, Wells Engineering

SmartRecruiters, Inc.; Minnesota; On-site; USD 110,000 - 160,000; Full time

Job summary

IPT Global is seeking a data scientist to apply machine learning to safeguarding wells in the energy industry. You will turn barrier assurance and verification data into predictions and recommendations that engineers and operators rely on, owning the work end to end.

You’ll work with experienced wells and integrity engineers to model real-world sensor data, develop monitoring, and explain results clearly to technical and leadership teams as models move into production.

Qualifications

• A degree in data science, computer science, statistics, engineering, physics, or related quantitative field.
• Strong proficiency in Python and data science ecosystem (pandas, NumPy, scikit-learn) with time series or anomaly detection experience.
• At least one model or analytical tool you built that was actually used to inform engineering or operational decisions.
• Solid grasp of statistics and model validation; ability to judge when an engineering assessment beats data.
• Experience with physical or sensor-derived data, ideally in oil and gas or wells engineering or similar industrial setting.

Responsibilities

• Build models to support pressure test interpretation (positive and inflow tests).
• Evaluate time series data from well control equipment and develop predictive maintenance models.
• Develop monitoring and anomaly detection for annulus pressure across the well lifecycle.
• Track barrier element status and verification history to surface gaps and prioritize work.
• Clean and structure data so models can trust it.
• Explain model results clearly to wells engineers, integrity teams, and leadership.

Skills

Python

Time series modeling

Anomaly detection

Predictive maintenance

Data visualization

Model deployment

Education

Bachelor's degree in data science, computer science, statistics, engineering, physics, or related quantitative field

Tools

Pandas

NumPy

scikit-learn

SQL

Job description

We're looking for a data scientist who wants to apply machine learning to one of the most consequential problems in the energy industry: making sure wells are safe. You'll turn well barrier assurance and verification data into predictions and recommendations that engineering and operations teams use to make real decisions, and you'll own that work end to end, from framing the problem with domain experts to putting a working model in front of the people who need it.

This role is a strong fit for a data scientist with a track record of building models on real-world, physical data, ideally with some exposure to oil and gas or wells engineering. You'll work closely with experienced wells and integrity engineers who will help you build the domain knowledge; what we're looking for from you is strong modeling skills and the curiosity to understand the systems behind the data.

You'll work on data science on problems that matter: the work you contribute to helps operators confirm their wells are safe. As part of a small team, you'll get real responsibility early, direct access to industry experts, and a front-row view of how analytics products are built in the energy industry.

Job Description

What you'll work on

• Building models to support pressure test interpretation, including positive and inflow tests
• Evaluating time series data from well control equipment, such as BOPs and associated control systems, and developing predictive maintenance models
• Developing monitoring and anomaly detection models for sustained or abnormal annulus pressure behavior across the well lifecycle
• Tracking barrier element status and verification history to surface gaps and prioritize integrity work
• Cleaning and structuring data into something models can trust
• Explaining model results clearly to wells engineers, integrity teams, and leadership, including when the model shouldn't be trusted

Qualifications

What you bring

• A degree in data science, computer science, statistics, engineering, physics, or a related quantitative field
• Strong proficiency in Python and its data science ecosystem (pandas, NumPy, scikit-learn, and similar), with experience in at least one of time series modeling, anomaly detection, or predictive maintenance
• At least one model or analytical tool you built that was actually used to inform engineering or operational decisions
• A solid grasp of statistics and model validation, and the judgment to know when an engineering assessment beats a data-driven one
• Experience working with physical or sensor-derived data, ideally in oil and gas, wells engineering, or well integrity, or in another industrial setting such as manufacturing, energy, or aerospace

Nice to have

• Hands-on wells engineering or well integrity experience at an operator, drilling contractor, or oilfield services company
• Familiarity with well integrity management systems or barrier assurance workflows
• Exposure to cloud platforms or deploying models into production
• SQL experience

Additional Information

At IPT Global your models won't die in a pilot. With a team of around 100 people, you'll work directly with the people making operational decisions and see the impact of your work quickly.