PhD Position – AI-Driven Modelling for Complex Fluid Dynamics in Aerospace Applications (FairCF[...]

Universidad Politécnica de Madrid, ETSIAE; España; Presencial; EUR 25.000 - 30.000; Jornada completa

Descripción de la vacante

A leading technical university in Spain is offering a PhD position focusing on developing innovative computational fluid dynamics models in collaboration with Airbus. Candidates should have a strong background in fluid mechanics and numerical simulation, along with a master's degree in a related field. The role includes engaging in cutting-edge research and gaining invaluable training in an international setting, starting between March and September 2026.

Formación

• Solid background in fluid mechanics and numerical simulation required.
• Interest in interdisciplinary research and open science highly appreciated.
• Experience in machine learning is valued.

Responsabilidades

• Contribute to technological innovation in the aerospace industry.
• Develop hybrid machine learning reduced-order models for industrial fluid dynamics.
• Validate models on industrial-scale data.

Conocimientos

Fluid mechanics

Numerical simulation

Machine learning

Educación

Master’s degree in Aerospace Engineering or equivalent

Descripción del empleo

Organisation/Company Universidad Politécnica de Madrid, ETSIAE Department Matemática Aplicada a la Ingeniería Aeroespacial Research Field Engineering Researcher Profile First Stage Researcher (R1) Positions PhD Positions Country Spain Application Deadline 30 Apr 2026 - 00:00 (Europe/Brussels) Type of Contract Permanent Job Status Full-time Hours Per Week 37.5 Offer Starting Date 1 Jun 2026 Is the job funded through the EU Research Framework Programme? Horizon Europe (other) Reference Number PID101226482 Is the Job related to staff position within a Research Infrastructure? No

Offer Description

This is much more than just a PhD position — it’s a unique opportunity to be part of the FairCFD Doctoral Network, an ambitious European training programme dedicated to building the future of sustainable, efficient computational fluid dynamics (CFD).

As a Doctoral Candidate at UPM, you will:

• Contribute to technological innovation in the aerospace industry, in close collaboration with Airbus, by developing advanced, efficient CFD strategies.
• Advance AI for Science, creating hybrid machine learning models that combine data-driven architectures with physical principles to simulate complex flow phenomena.
• Join a vibrant international network of 15 PhD researchers across 9 European countries, participating in interdisciplinary projects, secondments, and high-level training.

Scientific background

Accurately simulating nonlinear, multi-scale flows — such as sloshing in aircraft fuel tanks — remains a grand challenge in CFD. Conventional methods are computationally demanding and limit real-time or uncertainty analyses.

Recent advances in Artificial Intelligence (AI) and Scientific Machine Learning (SciML) offer transformative potential: by embedding physical constraints within neural architectures, we can achieve high accuracy, interpretability, and computational efficiency.

Your research will focus on developing hybrid machine learning reduced-order models (ROMs) for industrial fluid dynamics, using Airbus’s high-fidelity databases. The goal: next-generation digital twins for aerospace systems and beyond.

Objectives

• Develop hybrid AI–physics models integrating modal decomposition (POD, DMD, Koopman) with neural networks (CNNs, LSTMs, Transformers).
• Design interpretable models that respect conservation laws and physical symmetries.
• Validate models on industrial-scale data (sloshing dynamics in aircraft fuel tanks).
• Generalize the methodology to other turbulent and multiphase flows.
• Deliver scalable, low-cost AI tools for industrial CFD applications.

You will join ModelFLOWs, a leading research group at UPM’s School of Aerospace Engineering, specializing in scientific machine learning, reduced-order modeling, and CFD. The group works at the intersection of AI, physics, and high-performance computing, developing interpretable and efficient tools for real-world engineering impact.

Network integration & secondments

You will contribute primarily to WP2: Efficient data-based approaches and collaborate closely with other Doctoral Candidates.
Planned secondments include:

• Airbus (6 months): generating industrial datasets and testing ML models.
• IMFT (2 months): validating tools against complementary methodologies.

Interdisciplinary challenge – Numerical sustainability

As part of WP5, all FairCFD doctoral candidates will engage in a network-wide effort to define numerical frugality — assessing computational cost, energy consumption, and resource impact of simulations. The outcome will inform sustainable scientific computing practices across Europe.

Training programme

As a Marie Skłodowska-Curie Actions (MSCA-DN) fellow, you will benefit from an exceptional network-wide training experience, including:

• Four in-person training events: induction, technical & transferable skills accelerator, hackathon, and career development forum.
• Five online courses on advanced simulation, AI, open science, and sustainability.
• Participation in scientific and societal events such as symposia, hackathons, and colloquia.

This programme will equip you to become a leader in responsible and innovative simulation science.

Eligibility and requirements

• Master’s degree (or equivalent) in Aerospace Engineering, Mechanical Engineering, Applied Mathematics, Physics, or related field.
• Solid background in fluid mechanics and numerical simulation; experience in machine learning is highly valued.
• Proficiency in English (spoken and written).
• Mobility rule: candidates must not have resided or carried out their main activity in Spain for more than 12 months in the 36 months prior to recruitment (MSCA eligibility).

Application

The application process will be officially opened in February 2026. Meanwhile, additional information can be obtained by contacting the supervisors along with the DN coordinating team. For this sake, please contact us by e-mail [e-mail] , mentioning “[FairCFD] application to DC3” in the subject of the e-mail.

Additional comments

A start date will be negotiated with the successful candidate. Ideally start dates would be between March 2026 and September 2026, with a potential to extend the start date to October 2026.

Where to apply

E-mail [e-mail]

Requirements

Research Field Engineering » Mechanical engineering Education Level Master Degree or equivalent

Skills/Qualifications

• Master’s degree (or equivalent) in fluid mechanics, applied mathematics, scientific computing, or related fields.
• Strong background in fluid mechanics, numerical methods, PDEs, and/or data-driven modeling.
• Interest in interdisciplinary research and open science.