Research Engineer in LLM-based scientific agents

Job description

We are seeking to hire a research engineer to address uncertainties in LLM-based scientific agents. In the project, you will (i) identify potential sources of uncertainties in AI agents, (ii) investigate ways to assess the quality of uncertainty estimates by standard methods for LLMs, and (iii) develop a benchmark for uncertainty quantification in LLM-based scientific agents.

The project will be carried out under the supervision of Martin Trapp and Hossein Azizpour, and you will participate in regular group meetings. Moreover, during the project, a scientific one-day workshop with leading international researchers and collaborators will be planned and held, during which intermediate results will be presented. Additionally, results will need to be presented at the EECS Research and Impact Day in the summer of 2026.

Qualifications

Requirements

• A graduate degree or an advanced level (higher education) in the research subject or equivalent competence. 
• Experience with deep learning and machine learning tooling.·   
• In-depth knowledge of LLMs and Transformer architectures
• Excellent programming skills in PyTorch/JAX and experience working with GPUs and high-performance clusters.
• Strong mathematical skills with excellent understanding of statistics (e.g., hypothesis testing, Bayesian statistics)
• Good collaborative abilities, independence, and critical thinking.

Preferred qualifications

• In-depth experience with LLM agents
• Experience with uncertainty quantification in LLMs
• Experience in Bayesian deep learning
• Experience with Deep Generative Models
• Experience in conducting large-scale experiments
• Awareness of diversity and equal opportunity issues, with specific focus on gender equality

Great emphasis will be placed on personal skills.

Join us at KTH

KTH shapes the future through education, research and innovation. As a leading international technical university, we play an active role in advancing the transition towards a sustainable society. At KTH, you have the opportunity to grow and develop in a creative and dynamic environment, with good working conditions and attractive benefits. Equality, diversity and equal opportunities are essential to quality and form an integral part of KTH’s core values as a university and public authority.

Learn more about our benefits and what it's like to work and grow at KTH.

Trade union representatives

Contact information to trade union representatives.

To apply for the position

Log into KTH's recruitment system to apply for this position. You are responsible for ensuring that your application is complete according to the instructions in the ad.

The application must include:

1. CV including information on relevant experience (in English).
2. Brief account of how your practical experience relates to the project and why you would like to pursue this position (max 1 page, in English).

Your complete application must be received by KTH no later than the last day of application, midnight CET/CEST (Central European Time/Central European Summer Time).

About the employment

The employment is valid for a limited time according to the agreement - for up to 6 months, with access according to agreement.

Other information

For information about processing of personal data in the recruitment process.

It may be the case that a position at KTH is classified as a security-sensitive role in accordance with the Protective Security Act (2018:585). If this applies to the specific position, a security clearance will be conducted for the applicant in accordance with the same law with the applicant's consent. In such cases, a prerequisite for employment is that the applicant is approved following the security clearance.

We firmly decline all contact with staffing and recruitment agencies and job ad salespersons.

Disclaimer: In case of discrepancy between the Swedish original and the English translation of the job announcement, the Swedish version takes precedence.