Researcher Computation and Modeling

**The Role**:

- The QRM (Quantitative Reservoir Management) team develops algorithms and workflows that incorporate subsurface data (production data, [3D/4D] seismic, geologic, core, petrophysical, etc.) in modelling and decision making. Workflows extends from geology (static modeling) to seismic (attributes, inversion) to flow simulation (history matching, optimization). The computational aspects include uncertainty capture with statistical methods, optimization, multi-core parallel computing, machine learning and AI. The program is delivered in collaboration with multiple leading external technology partners (Texas A&M, TUPREP University of Tulsa, Unicamp Brazil). As a part of a 'data driven and proxy modelling and optimization' project, machine learning and 'big data' tools are becoming an important component of the team's toolset. Developing and/or deploying new innovative data driven solutions for the subsurface domain to improve performance of existing technologies to speed up decision making is crucial. QRM is developing new initiatives in Digital WRFM, CCUS and specialized optimization techniques with reduced order modelling. It is equally important to document learnings in the form of reports/articles to disseminate research, both internally and externally.

Dimensions
- Drive research through the Technology Maturation Funnel from ideation to deployment: lead smaller projects in the new initiatives QRM is venturing into such as: Digital WRFM, reduced order modeling, optimization
- Steer smaller projects and field trials
- Work directly with the business/assets in deployment activities, capture value generated
- Initiate/Steer External Research Collaborations in the fields of Reservoir engineering, Statistics & Data Science, liaising with academics, steering the research and protecting Shell’s interests by transferring external research into Shell’s business environment.

**Requirements**:

- Masters/Ph.D. level education in relevant discipline (Computer Science, Physics, Mathematics, Earth Sciences, Engineering) or equivalent experience.
- Skilled in Machine Learning algorithms and best practices regarding statistical validation techniques. Constructs complex data-driven models, including advanced machine learning.
- Strong analytical mindset, ability to deal with sometimes conflicting data on different scales, uncertainties in data and model parameters.
- Strong programming, software engineering, high-performance and scientific computing skills, and knowledge.
- Ability to work in a large code base, taking interdependencies into account. Able to port models/code across hardware platforms and (re)validate the results.
- Understands and applies software quality management tools like GitHub/VSTS (version management) and code reviews.
- Familiarity with digital technology deployment process. Setting up CI/CD pipelines, collaborative code development and deployment process. Knowledge of importance of various technology scan methods from security and code standard perspective.
- Knowledge of programming languages: Python, C++, Bash Scripting.
- Understanding of various hardware compute platforms and architectures.
- Familiarity of subsurface fundamentals e.g., Reservoir Engineering, Fluid Flow through Porous Media is a bonus.
- Information and different
- Self-drive. Well organized. Precise. Rigorous. Eager to deliver.
- Ability to communicate clearly and concisely verbally and in writing, to various audiences
- The ability to work in a multi-disciplinary environment, communicating deep technical considerations to scientists in other fields, in a simple and coherent manner.
- Ability to patiently educate end stakeholders with new digital skills and technologies.
- Project management at knowledge level
- A commercial mindset - where are the $$$?
- Flexibility to cope with peers and customers in teams around the globe.
**Disclaimer