PhD (d/f/m) within Improvement of AI methodologies for loads in-service support

Job Description:

You are looking for a PhD thesis and want to get to know the work of a flight physicist? Then apply now! We look forward to you supporting us in the Flight Physics capability department as a PhD Student (d/f/m)!

• Location: Hamburg, Finkenwerder

• Start: As soon as possible

• Duration: 3 years

• Part-time (20h)

Introduction

The benefit of artificial intelligence (AI) and the way this methodology can help data generation, process automation, or in this case, decision making, is more and more attractive also for the aerospace industry. In particular, the increasing adoption of neural network (NN) based methodologies has highlighted the importance of understanding and quantifying the uncertainty associated with their predictions. 

In the area of in-service support, i.e. providing support to the flying Airbus fleet, the engineering community is often confronted with decisions on whether a plane can continue flying after a potential incident. Airbus is researching ways to use the benefits provided by AI to enhance the robustness of the decision making and improve the response time to the customers.

Proposed Approach

The candidate will have the opportunity to work in two key aspects of this process chain. On the one hand, increasing the accuracy of the model and its capacity to describe the desired hyperspace while keeping the number of calculations to a level that is affordable and sustainable is of utmost importance. In order to do this, the research and comparison of different Design of Experiments (DoE) methods for a given use case can be performed in order to improve the data generation efficiency and achieve better modelling results.

On the other hand, ensuring the quality of the predictions and not only their accuracy is essential to ensure safe and good quality decision making. While point estimates from NNs provide valuable insights into the expected outcomes, they do not capture the complete picture of uncertainty, and therefore, are not as safe as we would require for in-service decision making. Model uncertainty, encompassing both epistemic and aleatoric uncertainty, provides a more comprehensive understanding of the reliability and limitations of neural network models. Evaluating and interpreting model uncertainty is essential for informed decision-making, risk assessment, and building trust in the predictions.

Your location

Hamburg is a charming city full of history in the northwest of Germany. In addition to being one of the country’s greenest cities, it offers wonderful sights, a rich culture, urban flair and culinary delights. It’s also a great place for kitesurf and sailing lovers, being located just by the Elbe and enjoying great sports areas!

Your benefits

• Work-life balance with a 20-hour week (flexitime).

• Mobile working after agreement with the department.

• Travelling internationally or within Germany (team events) is possible after consultation and agreement from the department.

• International environment with the opportunity to network globally.

• Work with modern/diversified technologies.

• At Airbus, we see you as a valuable team member and you are not hired to brew coffee, instead you are in close contact with the interfaces and are part of our weekly team meetings.

• Opportunity to participate in the Generation Airbus Community to expand your own network.

Your tasks and responsibilities

• Research and adapt existing DoE techniques to the presented problem and integrate some of the methods within our data generation software and infrastructure

• Support in the retraining and analysis of the existing models using the newly created input parameter space

• Explore different statistical methods to describe the accuracy and quality of the results

• Apply the aforementioned methods within the given analysed problem and ensure that the results are in line with the quality standards required by certification

Desired skills and qualifications

• Enrolled student (d/f/m) in the area of data science, mathematics, statistics, physics, computer science or an equivalent field of study.

• Broad experience with Python programming, Data Science, Machine Learning and Deep Learning is a must.

• Experience in the field of statistics is desired

• Notions of either Design of Experiment or AI explainability are desired

• Fluent in English.

Please upload the following documents: cover letter, CV, certificate of enrolment.

Not a 100% match? No worries! Airbus supports your personal growth.

Take your career to a new level and apply online now!

This job requires an awareness of any potential compliance risks and a commitment to act with integrity, as the foundation for the Company’s success, reputation and sustainable growth.

Company:

Employment Type:

-------

Experience Level:

Job Family:

By submitting your CV or application you are consenting to Airbus using and storing information about you for monitoring purposes relating to your application or future employment. This information will only be used by Airbus.
Airbus is committed to achieving workforce diversity and creating an inclusive working environment. We welcome all applications irrespective of social and cultural background, age, gender, disability, sexual orientation or religious belief.

Airbus is, and always has been, committed to equal opportunities for all. As such, we will never ask for any type of monetary exchange in the frame of a recruitment process. Any impersonation of Airbus to do so should be reported to emsom@airbus.com.

At Airbus, we support you to work, connect and collaborate more easily and flexibly. Wherever possible, we foster flexible working arrangements to stimulate innovative thinking.