Postdoctoral Research Fellow in AI-Driven Reservoir Simulation and Optimization

Hamad Bin Khalifa University (HBKU) invites applications for a Postdoctoral Research Fellow position to join a groundbreaking project focusing on the application of advanced machine learning (ML), artificial intelligence (AI), and large language models (LLMs) to revolutionize subsurface resource characterization, reservoir behavior simulation, and future production forecasting in Qatar's oil and gas sector.

Key Responsibilities

1. Machine Learning Framework Development
Design, develop, and implement ML models for reservoir characterization:

Integrate static (e.g., geological data) and dynamic (e.g., production and well data) inputs to predict key reservoir properties such as permeability, porosity, and fault structures.
Conduct feature engineering to identify and extract relevant relationships between reservoir variables.
Optimize model training processes using advanced ML libraries (e.g., TensorFlow, PyTorch) and GPU acceleration.
Apply uncertainty quantification techniques, such as Monte Carlo simulations, to validate model reliability.

2- Artificial Intelligence and Reinforcement Learning:

Implement reinforcement learning (RL) techniques for dynamic history matching and model refinement.
Develop reward systems and optimization frameworks to improve reservoir simulation accuracy.
Conduct iterative testing and refinement of RL models based on real-world datasets.

Qualifications

Essential:

A Ph.D. in Petroleum Engineering, Computational Science, Data Science, or a related field.

Strong expertise in machine learning frameworks such as TensorFlow, PyTorch, or equivalent.

Experience with reinforcement learning methodologies and applications in real-world scenarios.

Proven track record of scientific publications in reputable journals.

Proficiency in programming languages such as Python, C++, or MATLAB.

Familiarity with high-performance computing environments and parallel programming.

Desirable:

Background in reservoir simulation and modeling.

Experience working with industry-standard tools like Schlumberger’s Intersect or Eclipse.

Knowledge of subsurface data analysis, including seismic and well log interpretation.

Expertise in uncertainty quantification and risk analysis techniques.

Experience in developing and applying LLMs for engineering applications.

Strong interpersonal and communication skills for collaborative research and mentoring.

Duration: Full-Time, Three years.

Benefits

Competitive salary commensurate with experience.

Access to state-of-the-art computational facilities.

Opportunities for professional development through collaborations with leading academic and industrial partners.