Research Engineer in Scientific Generative Agents

Research Engineer in Scientific Generative Agents

KTH - Royal Institute of Technology

Stockholm, Sweden

Job description

We are looking to hire a research engineer to work full-time on 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, particularly with deep generative models, and (iii) develop a benchmark for uncertainty quantification in LLM-based scientific agents. The main application considered are going to be either on bio-molecules, fluid flow, or both depending on the background of the chosen candidate.

The project will be carried out under the supervision of Hossein Azizpour and Martin Trapp 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 deep generative models, 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.