Postdoctoral fellowship (2 years) within safe, secure and explainable AI architectures

The Department of Computing Science seeks a postdoctoral fellow to the project safe, secure and explainable AI architectures. The fellowship is full-time for two years with access June 2021 or otherwise agreed.

The Department of Computing Science (www.cs.umu.se) is a dynamic department with about 130 employees from over twenty countries. We are providing research and education within a broad spectrum of areas, and offer education on basic, advanced, and PhD levels. The research is internationally well recognized and includes basic research, methods development, and software development, and research and development within various application domains.

Project description

You will have the opportunity to focus on developing and evaluating novel methods, algorithms, and tools at the interface between safe, secure, and explainable AI. The project focuses mainly on automated reasoning techniques for software systems, correctness techniques for artificial intelligence (AI) applications, and explainable AI models. You will also have the opportunity to build use cases and collaborate with domain experts in autonomous systems.

The stipend project is financed by the Kempe foundations.

The stipend is full-time for two years with starting date of June 1st 2021, or to be negotiated. The stipend amounts to 330 000 SEK per year (around 32500 euro). The stipend is not subject to tax.

Qualifications

A Ph.D. in a relevant area (e.g., Computer Science, Computer/Electronics/Electrical Engineering, Mathematics) is a requirement. Priority should be given to candidates who have completed their doctoral degree no more than three years before the application's closing date. A candidate who has completed their degree before this may be considered if special circumstances exist. Special circumstances include absence due to illness, parental leave or clinical practice, appointments of trust in trade unions, or similar circumstances. This must be clearly stated in the application.

Other required qualifications:

- Excellent knowledge in at least one of the following areas:
     - Automated verification
     - Foundations of learning
     - Security of machine learning
     - Symbolic execution/abstract interpretation
     - Automated reasoning/first-order theorem proving
     - Explainable AI
     - Adversarial methods

- Strong coding skills
- Excellent communication, collaborative and interpersonal skills
- An excellent command of the English language, both written and spoken
- Ability to present in both written and oral publications

Other desirable qualifications:

- A track-record of high-quality publications
- Previous implementation experience with a formal analysis tool
-Knowledge and experience in software design and verification
- Knowledge and experience in reliability assessment of neural networks and concurrent systems
- Solid mathematical understanding of ML
- Proficient in PyTorch or TensorFlow (2+ years' experience).

Application

A full application should include:
- A cover letter summarizing your qualifications, research interests, and motivation for applying (max two pages)
- Curriculum vitae CV with publication list,
- Certified copy of doctoral degree certificate,
- Certified copies of other diplomas, list of completed academic courses and grades,
- Copy of doctoral thesis and possibly relevant articles,
- Contact information for at least two reference persons,

Submit your application as a PDF marked with the reference number FS 2.1.6-282-21, both in the file name and in the subject field of the email, to medel@diarie.umu.se. The application can be written in English (preferably) or Swedish. Application deadline is 18 April 2021.

We look forward to your application!