Research Fellow
at Heriot Watt University
Midlothian, Scotland, United Kingdom -
Start Date | Expiry Date | Salary | Posted On | Experience | Skills | Telecommute | Sponsor Visa |
---|---|---|---|---|---|---|---|
Immediate | 08 Nov, 2024 | GBP 56021 Annual | 09 Aug, 2024 | N/A | Physics,Optimization,Publications,Version Control,Continuous Integration,Software Testing,Applied Mathematics,Working Experience,Algorithms,Openfoam,Communication Skills | No | No |
Required Visa Status:
Citizen | GC |
US Citizen | Student Visa |
H1B | CPT |
OPT | H4 Spouse of H1B |
GC Green Card |
Employment Type:
Full Time | Part Time |
Permanent | Independent - 1099 |
Contract – W2 | C2H Independent |
C2H W2 | Contract – Corp 2 Corp |
Contract to Hire – Corp 2 Corp |
Description:
Salary: Grade 8 (£45,585-£56,021)
Contract: Full-time (35 hours per week), Fixed Term for 12 months with possible extension pending funding availability.
QUALIFICATIONS
- PhD in computational science & engineering, applied mathematics, physics or in a related computational field.
EXPERIENCE
- Prior experience in developing deep learning models using open-source libraries (e.g., PyTorch, JAX).
- Prior experience with open-source simulators (e.g., The MATLAB Reservoir Simulation Toolbox, JutulDarcy and/or OpenFOAM).
- Prior experience in developing control and optimization algorithms.
- Strong track record of publications in high impact scientific journals.
- Working experience in modern software development techniques (version control, continuous integration, software testing, etc).
- Excellent verbal and written communication skills, and ability to write professional reports.
When applying, please include a cover letter addressing these selection criteria.
Responsibilities:
PURPOSE OF ROLE
The successful candidate is expected to develop model-based control and optimization techniques for multi-scale flow modeling of CO2 in subsurface reservoirs including the development of simplified complexity models for an accelerated risk assessment and optimization algorithms. In addition, the successful candidate will contribute to a wide range of AI applications in subsurface flow modelling including (a) Deep learning proxy modelling with physics based losses and built-in model constrains (b) Efficient coupling of deep learning models to numerical solvers for hybrid CO2 flow modelling. The developed machine learning techniques will be open-sourced and be validated across a wide range of applications and on experimental data and direct numerical simulations generated by the project team.
The successful candidate will be part of a large multidisciplinary research project on maximising CO2 storage in deep geological formations. The candidate will benefit from interactions with the project team across Heriot-Watt university and Imperial College London including:
- Institute of GeoEnergy Engineering (IGE) at Heriot-Watt University
- Lyell centre at Heriot-Watt University
- Department of Earth Science and Engineering (ESE) at Imperial College London
KEY DUTIES & RESPONSIBILITIES
The successful candidate will be expected to undertake the following:
- Develop deep reinforcement learning algorithms for subsurface fluid control.
- Develop effective fluid flow emulators using deep learning techniques.
- Disseminate research results in peer reviewed journals and interdisciplinary conferences.
- Publish open-source code repositories demonstrating all developed techniques and associated computational notebooks, blogs, and presentation materials.
- Organize and lead Hackathons as a part of ECO-AI project activities.
- Participate in regular project meetings with team members and project sponsors.
REQUIREMENT SUMMARY
Min:N/AMax:5.0 year(s)
Information Technology/IT
IT Software - Other
Software Engineering
Phd
Proficient
1
Midlothian, United Kingdom