Petrophysicist

The University of Texas at Austin • Austin, TX

39d • $70,000 • Onsite

About The Position

We are seeking a highly motivated candidate for a petrophysicist position within the Bureau of Economic Geology's State of Texas Advanced Resource Recovery (STARR) group. The purpose of this position is to develop an integrated, end-to-end subsurface characterization workflow that supports subsurface energy storage projects by transforming raw well-log data into 3-D geologic and facies models for site evaluation and design. The role will lead the analysis, QA/QC, conditioning, and standardization of well logs using reproducible Python pipelines, then curate and organize the filtered datasets within a structured Petrel project. The position will build and validate machine-learning electrofacies classifications that will ultimately be used to generate 3-D facies models in Petrel. A core part of the work is applying geostatistical methods—variogram, kriging, and sequential gaussian simulation (SGS) modeling—to generate facies realizations that honor well control and geologic continuity while quantifying uncertainty.

Requirements

• Master's degree and at least 2 years of experience in Petroleum Engineering, Geosciences, or a related discipline.
• Must have a strong background in petrophysics and well log interpretation, including log QA/QC and conditioning and normalization workflows.
• Candidate must be proficient in Python packages used for subsurface data analysis (pandas/numpy/scipy, matplotlib, plotly) and well-log analysis (lasio, welly) and have experience building reproducible workflows.
• Must have proficiency building machine-learning models (bagging, boosting, support vector machines, artificial neural networks) for electrofacies classification using Python libraries such as scikit-learn, TensorFlow/Keras, and PyTorch.
• Solid knowledge of geostatistical methods used in modeling and uncertainty quantification.
• Relevant education and experience may be substituted as appropriate.

Nice To Haves

• PhD in Petroleum Engineering, Geosciences, or a related discipline, with specialization in petrophysics (log interpretation, rock properties, and reservoir characterization).
• Understanding of geologic controls on facies architecture and how to translate concepts into modeling domains, trends, and constraints.
• Understanding of advanced geostatistical workflows, such as co-kriging / co-simulation and indicator kriging.
• Hand-on experience with Petrel, including well data management, templates, interpretation integration, static model building, and property modeling.
• Familiarity with industry-standard petrophysical modeling packages, such as IP.

Responsibilities

• Conduct data analysis, including QA/QC and conditioning of raw well log data (LAS files) using reproducible Python workflows.
• Load conditioned logs and associated well data to Petrel.
• Develop, train, validate, and apply machine-learning electrofacies classification models (bagging, boosting, SVM, ANN) using well-log-derived features; evaluate performance with appropriate metrics; load resulting output facies curves into Petrel.
• Collaborate with other BEG personnel to use geostatistical analysis and modeling to generate and distribute 3-D facies and property models within Petrel.
• Integrate model results to inform subsurface energy storage assessments, including capacity assessment, and risk-focused subsurface studies.
• Communicate technical results and project outcomes through peer-reviewed journal manuscripts, conference abstracts/proceedings and presentations, and updates to partners/stakeholders in meetings.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level