Internship | Logistic modeling by human-LLM cooperation

Internship | Logistic modeling by human-LLM cooperation

About this position

Domain-Specific Languages (DSLs) are central to modern software and systems engineering. They provide abstraction, formalization, and automation that help engineers manage complexity and reason about systems. DSLs support tasks such as design, analysis, verification, and synthesis, forming the foundation of many model-based methodologies.

What will be your role?

Despite their advantages, the adoption of model-based approaches remains limited. Creating and maintaining models using DSLs often requires deep domain expertise, familiarity with specialized DSL syntax, semantics and tools. This complexity restricts accessibility for non-experts and slows iterative design cycles, reducing the broader impact of model-based approaches in real-world engineering projects.

Recent advances in AI, particularly in Large Language Models (LLMs), present new opportunities to address challenges in modeling and system design. LLMs exhibit remarkable capabilities in understanding natural language, generating structured artifacts, and adapting to specialized domain vocabularies. Moreover, agent-based AI allows collaboration with humans within engineering workflows.

In this assignment, you will explore how the recent advances in AI can be applied to creating logistic models using the Logistic Specification and Analysis Tool (Eclipse LSAT). LSAT allows logistic systems to be modeled in terms of four interdependent DSLs and then analyzed with respect to timing and resource usage.

In your assignment, you will to assess whether LLMs/AI-based approaches can be provide design assistance to make it easier to create LSAT models for a given system, without requiring extensive experience with LSAT. You will study two research questions:

1. To what extent can LLMs generate syntactically and semantically correct LSAT models from natural-language descriptions?
2. To what extent can an LLM-based component with human-in-the-loop interaction be incorporated into the LSAT modeling environment?

To address these research questions, you will develop LLM-based solutions to create LSAT models. To evaluate the practical applicability your solutions, you will use a rigorous approach that provides understanding of the solutions’ strengths as well as their limitations.

What we expect from you

You are a Master student in Artificial Intelligence or Computer Science looking for a graduation internship of 6-9 months. You have affinity with DSLs and/or system modelling. Moreover, you would like your graduation project to show the benefits of scientific system development methods in a high-tech organization.

What you'll get in return

You want an internship opportunity on the precursor of your career; an internship gives you an opportunity to take a good look at your prospective future employer. TNO goes a step further. It’s not just looking that interests us; you and your knowledge are essential to our innovation. That’s why we attach a great deal of value to your personal and professional development. You will, of course, be properly supervised during your work placement and be given the scope for you to get the best out of yourself. Furthermore, we provide:

• A highly professional, innovative internship environment, within a team of top experts.
• A suitable internship allowance (615 euro for wo-, hbo- and mbo-students, for a full-time internship).
• Possibility of eight hours of free leave per internship month (for a full-time internship).
• A free membership of Jong TNO, where you can meet other TNO professionals and join several activities, such as sports activities, (work-related) courses or the yearly ski-trip.
• Use of a laptop.
• An allowance for travel expenses in case you don’t receive an OV-card.

TNO as an employer

At TNO, we innovate for a healthier, safer and more sustainable life. And for a strong economy.