Vacant job

Umeå University is one of Sweden's largest higher education institutions, with over 41,500 students and approximately 4,600 employees. The university offers a diverse range of high-quality education and world-leading research across several scientific fields, including the groundbreaking discovery of the gene-editing tool CRISPR-Cas9, which was awarded the Nobel Prize in Chemistry. At Umeå University, everything is close. Our cohesive campuses make it easy to meet, collaborate, and exchange knowledge, fostering a dynamic and open culture.

Interested in learning more? Read more about Umeå University as an employer.

To our department, which conducts world-class international research and offers several high-quality educational programs, we are now seeking a postdoctoral researcher to work on data privacy methods for data-driven models. The position is full-time for two years, with a start date of January 8, 2027, or as agreed.

The Department of Computing Science at Umeå University is an international environment for research and education within a broad spectrum of computer science. The department is internationally renowned for its excellent research and teaching. Read more at the Department of Computing Science (https://www.cs.umu.se).

Project Description and Responsibilities

The project will develop privacy-aware models for machine learning (ML). We are interested in data-driven models for complex data, including temporal data. We are interested in both data-driven models and models based on synthetic data.

Regarding privacy, we focus on various types of privacy measures and models (differential and integral privacy, k-anonymity), as well as different scenarios (centralized and decentralized data; local and global privacy). For decentralized data, we consider federated learning.

We are interested in large-scale privacy-preserving machine learning.

Research Group

The research group "Privacy-aware transparency decisions," led by Professor Vicenç Torra, researches data integrity for data to be used in machine learning and statistical analysis. It is well known that data can be highly sensitive and that naive anonymization is not sufficient to prevent disclosure. Models and aggregates can also lead to disclosure as they may contain traces of the data used in the calculation. We aim to understand the fundamental principles that enable us to build privacy-aware AI systems and develop algorithms for this purpose. For more information, see: umu.se/en/research/groups/nausica-privacy-aware-transparent-decisions-group-/ (https://umu.se/en/research/groups/nausica-privacy-aware-transparent-decisions-group-/)

The postdoctoral position is funded by the Wallenberg AI, Autonomous Systems and Software Program (WASP), Sweden's largest single research program in modern times. The program creates a platform for academic research and education in close collaboration with leading Swedish technology-intensive industry. The research includes artificial intelligence and autonomous systems that operate in collaboration with humans and adapt to their surroundings using sensors, information, and knowledge, creating intelligent systems of systems. WASP's vision is excellent research and competence in artificial intelligence, autonomous systems, and software for the benefit of Swedish industry and society. Read more: https://wasp-sweden.org/ (https://wasp-sweden.org/)

Qualifications

To be employed under an agreement for a fixed-term position as a postdoctoral researcher, a completed PhD degree or a foreign degree assessed as equivalent to a PhD is required. This eligibility requirement must be met no later than at the time the employment decision is made.

To be employed under the postdoctoral agreement, preference is given to those who have completed the degree mentioned in the previous paragraph within the last three years. If there are special reasons, those who obtained their PhD degree earlier may also be considered. Special reasons include leave due to illness, parental leave, trust positions within trade unions, service in the total defense, or other similar circumstances, as well as clinical service or service/assignments relevant to the subject area.

A qualified applicant must hold a PhD degree or a foreign degree assessed as equivalent in computer science or another subject relevant to the project.

Documented knowledge and proven research experience in the field of algorithm design and methods for data protection and machine learning are required. Publications in leading conferences within machine learning, security, and privacy (such as NeurIPS, ICML, S&P, PETs, ESORICS, or similar conferences) are highly meritorious.

A successful candidate is expected to have a scientific and results-oriented approach to their work. Very good knowledge of the English language, both spoken and written, is a key requirement.

Application

A complete application should include:

• A cover letter describing your research interests and why you are applying for the advertised position. Summarize your qualifications, research interests, motivation for applying, and describe the connection between your previous research and the position (max 2 pages),
• Curriculum Vitae (CV) with a publication list,
• Certified copy of the PhD degree certificate or documentation confirming when the PhD degree is expected to be obtained,
• Certified copies of other degree certificates, academic course certificates and/or grades,
• Copy of the doctoral thesis and a maximum of 5 relevant articles,
• Other documents that the applicant wishes to submit.
• Contact details for two professional references.

The application must be written in English or Swedish. Applications are submitted through our electronic recruitment system. Documents sent electronically must be in Word or PDF format. Log in to the system and apply via the button at the end of this page. The last day for applications is August 9. For further information, please contact Vicenç Torra at [email protected].

To staffing and recruitment agencies and to you who are sales representatives: We kindly but firmly decline direct contact with staffing and recruitment agencies as well as sales of additional job advertisements.