Project / Job description

A 3-year PhD Research Fellowship is available at Simula Metropolitan Center for Digital Engineering (SimulaMet), within our research effort on the security and safety of AI systems.

Most security and safety work on AI happens where models are built. We work where they are used. As AI systems move into hospitals, public administration, and other consequential settings, the institutions that deploy them, and the regulators and auditors who oversee them, need to establish whether a given system is safe to use, independently of the vendor that built it. Today, they largely cannot. Closing that gap is the purpose of this position, and it grows more urgent as accountability shifts toward the organisations that deploy and audit AI, not only those that train it.

The PhD researcher will develop methods and tools for evaluating, red-teaming, and monitoring AI systems as they are actually deployed, large language models today, and increasingly agentic and multimodal systems. The work pursues two goals at once:

• A science of failure. Not counting failures, but explaining why and when systems fail, so that findings generalise beyond the single system tested. This means treating a model as one part of a larger socio-technical system, evaluating data, training, deployment, and feedback continuously rather than once, and weighting the catastrophic 1% over the comfortable 99% average.
• Open, vendor-independent tools. Practical, local-first instruments that any regulator, auditor, hospital, or public agency can run without commercial dependencies and without access to the vendor of the system under test.

You would build on and extend an existing, openly released toolset: SimpleAudit (scenario-based safety auditing; a verified Digital Public Good), swarm-attack (adversarial swarm red-teaming), and the Moltbook Observatory (passive monitoring of deployed agents). The precise direction will be shaped together with you and the supervisory team, and may emphasise scenario-based auditing, adversarial and swarm red-teaming, agentic-system security, continuous monitoring, multilingual and national-language deployment, or the methodology of evaluation itself. 

A defining strength of the group is direct collaboration with the institutions where failure is costly, including partners across Norwegian public health and the public sector, which grounds the work in real deployment contexts rather than synthetic benchmarks.

The purpose of a PhD fellowship is to qualify the candidate for work in positions that require a high level of scientific competence, leading to the award of a doctoral degree (PhD). The successful candidate will be admitted to a doctoral (PhD) programme at OsloMet - Oslo Metropolitan University. A career development plan will be drawn up for the fellow, and SimulaMet is responsible for following up on this plan and ensuring access to supervision and career guidance throughout the period. Research stays abroad and presentation of results at international and national conferences are facilitated and strongly encouraged, and training and support for academic writing are provided throughout the fellowship.

Candidate Profile

We will consider candidates who have (or will have completed before the start of the position) a Master's degree (or equivalent) in Computer Science, Applied Mathematics, or another relevant discipline. The applicant is required to demonstrate how the degree corresponds to the profile of the post. Other qualifications include:

• A strong background in machine learning, data science, benchmarking and evaluation of AI systems, AI security and safety, AI alignment or a closely related area.
• Research experience, demonstrated for example through a strong Master's thesis, and ideally through publicly released code or publications.
• Proficiency in a high-level programming language (e.g., Python).
• Excellent oral and written communication skills in English.
• An open and collaborative mindset, with the ability to work effectively across disciplines and in culturally diverse teams.

Experience with large language models, red-teaming or adversarial testing, AI evaluation, or safety-critical / high-stakes application domains (e.g., healthcare, public sector) is an advantage but not a requirement.

Simula Offers

• Excellent opportunities for performing high quality research, as part of a highly competent and motivated team of international researchers and engineers.
• An informal and inclusive international working environment.
• Generous support for travel and opportunities to build international networks, through established collaboration with industry and the public sector, exchange programmes and research visits with other universities, and funding to attend conferences.
• Modern office facilities located in downtown Oslo.
• A competitive salary. Starting salary from NOK 550 800.
• Numerous benefits: access to company cabin, sponsored social events, generous equipment budgets (e.g., computer, phone and subscription), subsidised canteen meals, comprehensive travel/health insurance policy, etc.
• Relocation assistance: accommodation, visas, complimentary Norwegian language courses, etc.
• Administrative research support.
• Wellness and work-life balance. Our employees' health and well-being is a priority, and we encourage them to make use of our flexible work arrangements to help balance their work and home lives efficiently.

Application

Interested applicants are requested to submit the following:

• Curriculum vitae showing your educational background, working experience (in particular, any relevant academic or industrial work), and a list of any scientific publications and talks.
• Cover letter (approximately 2 pages) outlining your motivation for applying, relevant experience and qualifications, research interests, and how/why you are qualified for the position.
• Transcripts from Bachelor and Master degrees.
• Copy of your Master's thesis (or a draft, if it is not yet completed).
• Contact information of at least two references.

Please note that all documents must be in English. Do not submit other certificates, articles, and the like unless specifically requested. If further documentation is wanted for assessment, you will be asked to submit it later.

Deadline: 15.08.2026

Short-listed candidates will be invited for an interview. Expected starting date before the end of 2026.

Contact

Additional enquiries regarding the position can be addressed to Michael A. Riegler, michael@simula.no, who leads the group.

General Information

This position is part of SimulaMet's research on the security and safety of AI systems. The group develops measurement theory and open, vendor-independent tools for evaluating, red-teaming, and monitoring AI systems where they are deployed, with a focus on high-stakes domains such as healthcare, the public sector, and education. Its open toolset includes SimpleAudit, a lightweight, local-first framework for multilingual safety auditing and red-teaming via adversarial probing, developed together with partners including the Norwegian Directorate of Health, alongside swarm-attack (adversarial swarm red-teaming) and the Moltbook Observatory (passive monitoring of deployed agents).

For more information about SimulaMet and the research environment, see here. 

Employment for this position will be made according to the Security Act and the Act relating to Control of the Export of Strategic Goods, Services and Technology. Candidates who by assessment of the application and any attachments are considered to be in conflict with these regulations will not qualify for this position.

SimulaMet uses background checks in our recruitment process. All candidates are assessed for affiliation with high-risk countries. This assessment also considers whether the research area involves sensitive technologies, dual-use knowledge, critical infrastructure, or other security-relevant topics.

According to the Norwegian Freedom and Information Act (Offentleglova) information about the applicant may be included in the public applicant list, also in cases where the applicant has requested non-disclosure.