Reservoir Simulation Research Scientist – Machine Learning & Optimization Focus

About the Role:

We are seeking a highly motivated Reservoir Simulation Research Scientist to contribute to the next generation of reservoir modeling technologies. This role focuses on the research and development (R&D) of advanced computational methods combining physics-based reservoir simulation with machine learning, data assimilation, and optimization. You will work on developing novel algorithms, enhancing simulation capabilities, and bridging data-driven and physics-based modeling approaches to support the energy transition and improve reservoir management workflows.

Key Responsibilities:

Conduct fundamental and applied research in reservoir simulation, computational physics, and data-driven methods.

Develop and prototype novel algorithms that integrate machine learning with traditional reservoir simulation workflows, including surrogate modeling, reduced-order modeling, and hybrid physics-ML models.

Research and implement advanced data assimilation techniques, including ensemble-based methods, adjoint-based gradient optimization, and Bayesian inference for history matching and uncertainty quantification.

Develop and apply optimization algorithms for field development planning, production enhancement, and reservoir control under uncertainty.

Collaborate with cross-disciplinary teams including reservoir engineers, geoscientists, data scientists, and software engineers.

Publish research outcomes in peer-reviewed journals, patents, and present at industry and academic conferences.

Provide technical leadership in framing R&D roadmaps, identifying high-impact research directions, and supporting technology transfer into commercial or operational tools.

Contribute to the development of internal software prototypes or production-grade software for reservoir modeling and AI-enabled workflows.

Required Qualifications:

Ph.D. in Petroleum Engineering or Reservoir Engineering or a related field with a focus on numerical simulation, optimization, or machine learning applications.

Strong background in numerical methods for PDEs, linear and nonlinear solvers, and reservoir flow physics.

Expertise in reservoir simulation technologies, including finite difference, finite volume, or finite element methods applied to multiphase subsurface flow.

Demonstrated research experience in one or more of the following:

Machine learning (e.g., surrogate modeling, neural networks, Gaussian processes, physics-informed ML)

Data assimilation (e.g., Ensemble Kalman Filter, Ensemble Smoother, Adjoint-based optimization, Bayesian inference)

Optimization (e.g., field development planning, well control optimization, robust optimization under uncertainty)

Proficiency in scientific programming (ideally Python and MATLAB) for algorithm development and prototyping.

Proven track record of peer-reviewed publications, conference presentations, or patents in relevant technical domains.

Preferred Qualifications:

Experience integrating physics-based simulation with machine learning frameworks, including Physics-Informed Neural Networks (PINNs) or hybrid models.

Knowledge of high-performance computing (HPC), parallel programming, or cloud computing for large-scale simulations.

Familiarity with open-source or commercial reservoir simulators (e.g., MRST, Open Porous Media, Eclipse, Intersect, tNavigator, CMG).

Experience with probabilistic modeling, uncertainty quantification, and decision-making under uncertainty.

Background in related domains such as CO₂ sequestration, geothermal systems, or unconventional resources modeling is a plus.

Soft Skills:

Strong analytical and problem-solving skills with a rigorous scientific approach.

Ability to communicate complex technical ideas clearly to both technical and non-technical audiences.

Self-driven, collaborative, and passionate about advancing the state of the art in reservoir engineering and computational sciences.

Comfortable working in both independent research settings and collaborative, multi-disciplinary environments.

Why Join Us?

Work on cutting-edge problems at the intersection of subsurface science, machine learning, optimization and computational physics.

Be part of a collaborative R&D team influencing the future of energy, carbon management, and sustainable subsurface technologies.

Opportunities to publish, patent, and contribute to open-source software or commercial products.

Competitive compensation, research freedom, and professional growth in a dynamic, innovation-driven environment.