Doctoral student in Applied Mathematics with a focus on Computer Vision and Spatial AI Full-time

Doctoral Student in Applied Mathematics with a Focus on Computer Vision and Spatial AI

Lund University was founded in 1666 and is repeatedly ranked among the world's top universities. The University has around 46,000 students and 8,500 staff based in Lund, Helsingborg, and Malmö. We are united in our efforts to understand, explain, and improve our world and the human condition.

Description of the Workplace

The position will be placed at the Division of Computer Vision and Machine Learning at the Centre for Mathematical Sciences. The Centre for Mathematical Sciences is a department affiliated with both the Faculty of Engineering (LTH) and the Faculty of Science at Lund University.

Within the division of Computer Vision and Machine Learning, there are several senior researchers and approximately 20 doctoral candidates. Research in this field began in the mid 1980s and currently encompasses (i) geometry and computer vision (including analysis of video, audio, radio, and radar signals), (ii) medical image analysis, and (iii) machine learning and artificial intelligence. The group has extensive experience in fundamental and applied research within computer vision, machine learning, and artificial intelligence, as well as a track record of translating such findings into practical applications for end-users.

Being a Doctoral Student

As a doctoral student, you are both admitted as a student and employed at Lund University. As a doctoral student, you will be trained in a scientific approach. In short, you will be trained to think critically and analytically, to solve problems independently using the right methods, and to develop an awareness of research ethics. In addition, you will have the opportunity to work on projects, to develop your leadership and pedagogical skills. Throughout your studies, you will be guided by supervisors. Doctoral studies end with a thesis and a doctoral degree.

Subject and Project Description

The research area for this position is computer vision and machine learning, with a focus on new end-to-end machine learning methods and foundational methods suitable for structure from motion research using audio. The research subject is mathematics.

Within our division, we have extensive experience in developing new methods for creating 3D models from sensor data, which are used in many applications, for example 3D maps for human navigation, mapping and localization for autonomous cars and other vehicles. We develop new methods, for example, feature extraction from sensor data, solving polynomial equations, and optimization.

The project is financed by the strategic research area ELLIIT and is part of the project “Next Generation Spatial AI”, that runs 2026-2031 as a joint project between Lund and Linköping, see ELLIIT. In this project, we will explore new methods for 3D modelling and sensor position estimation that operate directly on sensor data. Here, we will also use new so-called feature-metric approaches. These new modern deep-learning based approaches have the potential of revolutionizing the geometric understanding. We will in the project primarily study acoustic data and sensors, but the methods could also be applied to other sensor types.

The thesis work in the project will include the development of new methods, theoretical analysis, algorithm design, planning and execution of experiments, data collection, writing scientific articles, and presenting the results at international conferences.

Work Duties

You will primarily devote yourself to your doctoral programme, which includes participation in research projects as well as third cycle courses, seminars, and conferences.

The research area for the current call is computer vision and machine learning, with a focus on 3D mapping methods for audio. The project explores how to rethink such systems by constructing end-to-end methods that combines detection and tracking with 3D estimation. In the research we will study new methods of estimating positions and geometry directly from sound. Current methods rely on simplified measurements like timing differences, which capture basic geometry but miss much of the richness in real acoustic signals. Here, you will instead explore how learned representations from deep networks can used directly with 3D estimation, allowing the system to use more detailed signal in-formation such as motion effects, signal strength, and reverberations. By training these representations jointly with the estimation process, the goal is to create more accurate and robust methods that go beyond the limitations of traditional approaches.

The thesis work will include the development of new methods, planning and execution of experiments, data collection, programming and implementation, writing scientific articles, and presenting the results at international conferences.

The duties may also include participation in teaching and other departmental work (however, a maximum of 20% of working hours).

Qualifications

To be eligible for admission and employment as a doctoral student, you must fulfil the requirements below.

Admission Requirements

A person meets the general admission requirements for third-cycle courses and study programmes if the applicant:

• has been awarded a second-cycle qualification, or
• has satisfied the requirements for courses comprising at least 240 credits of which at least 60 credits were awarded in the second cycle, or
• has acquired substantially equivalent knowledge in some other way in Sweden or abroad.

A person meets the specific admission requirements for third cycle studies in applied mathematics if the applicant has:

• at least 90 credits of relevance to the subject area, of which at least 45 credits are from the second cycle.

Finally, the student must be judged to have the potential to complete the programme.

Exemptions from the admission requirements may be granted by the dean of LTH.

Additional Requirements

In order to complete the doctoral programme in question, the following are also required:

• good ability to work independently and to formulate and tackle research problems
• good written and oral communication skills
• good ability to cooperate
• very good knowledge of English, spoken and written.

Other Qualifications

For the doctoral programme in question, the following are considered as other qualifications:

Knowledge and skills relevant to the thesis project and the subject of study. An assessment of ability to work independently and to formulate and tackle research problems. Other experience relevant to the third-cycle studies, e.g. professional experience.

• Knowledge of computer vision.
• Knowledge of deep learning.
• Good programming skills in Python or C++.
• Experience with machine learning frameworks such as PyTorch.

We Offer

Lund University is a public authority which means that employees get particular benefits, generous annual leave, and an advantageous occupational pension scheme.

More about working at Lund University on lu.se.

About the Employment

The employment is a fixed-term employment at full time, starting before 1 October 2026. Third cycle studies at LTH consist of full-time studies for 4 years. In the case of teaching and other departmental duties, the employment is extended accordingly. Doctoral studentships are regulated in the Higher Education Ordinance (1993:100), chapter 5, 1-7 §§.

More about terms of employment for doctoral students on Lund University's Staffpages.

Other

We expect interviews for the position to be held either online or at the centre for Mathematical Sciences in Lund in the beginning of June.

How to Apply

Applications shall be written in English and include:

• CV and a cover letter stating the reasons why you are interested in the doctoral programme/employment and in what way the research project corresponds to your interests and educational background.
• Copies of issued study certificates and/or awarded degree certificates. These must confirm that you meet the general and specific admission requirements for the doctoral programme and show that you have the subject knowledge required for the doctoral programme project.
• Other documents you wish to be considered (grade transcripts, contact information for your references, letters of recommendation, etc.)

We welcome your application.