ML-Driven Research Scientist for Extreme Fluid Flows

Imperial Enterprise; Greater London; Sur place; GBP 42 000 - 60 000; Plein temps

Avantages offerts par ce poste

39 days off a year

Generous pension schemes

Travel to international conferences

Résumé du poste

Imperial College London invites applications for a Research Assistant or Associate in Computational and Machine Learning Tools for Extreme Events in Engineering Fluid Flows. The role focuses on developing hybrid simulation and machine learning tools to forecast and control extreme events in turbulent, reacting flows.

You will interface high-fidelity simulations with ML libraries and deploy on high-performance computing facilities, applying the framework to engineering-relevant flows such as

Qualifications

• PhD in Aerospace/Mechanical Engineering, Physics, Computer Science or closely related field.
• Strong background in CFD, HPC, ML, fluid mechanics.
• Reacting flow experience desirable but not required.

Responsabilités

• Develop computational methods for forecasting and control of extreme events in turbulent (reacting) flows.
• Interface high-fidelity simulation codes with machine learning libraries and deploy on HPC centers.
• Develop and apply the hybrid simulation/ML framework to flows such as flashback in hydrogen reacting flows.
• Collaborate within the CONTEXT ERC project and contribute to publishing and dissemination.

Connaissances

high-fidelity CFD

high-performance computing

machine learning

fluid mechanics

Formation

PhD in Aerospace Engineering or closely related discipline

Masters degree (for Research Assistant)

Outils

CFD software

Description du poste

Imperial College London invites applications for a Research Assistant or Associate in Computational and Machine Learning Tools for Extreme Events in Engineering Fluid Flows. The role focuses on developing hybrid simulation and machine learning tools to forecast and control extreme events in turbulent, reacting flows.

You will interface high-fidelity simulations with ML libraries and deploy on high-performance computing facilities, applying the framework to engineering-relevant flows such as