Master Thesis: Automated Test Case Generation for MiniZinc Models with Large Language Models
Om jobbet
Join our Team
About this opportunity:
MiniZinc is widely used to model complex configuration and optimization problems, especially in telecom systems. These models can be very large, and creating good test cases for them is time-consuming and often done manually. With recent progress in Large Language Models (LLMs), there is now an opportunity to explore whether AI can help automate this process.
This thesis explores how LLMs can be used to generate test cases for MiniZinc models. The focus is on understanding how well AI can interpret constraints, produce inputs and output, and support testing. Different approaches, prompting strategies, and model setups can be investigated to understand what works best in practice. The results can help Ericsson evaluate the potential of AI-assisted testing for constraint-based systems.
What you will do:
- Review relevant research on AI for code generation, automated testing, and constraint programming.
- Study a large MiniZinc model and understand the structure and purpose of its key constraints.
- Develop and test methods for generating MiniZinc test cases using LLMs.
- Build a workflow where the LLM creates test cases and the MiniZinc solver checks them.
- Explore and compare different ways of using LLMs for this problem (e.g., different prompting strategies, workflows, or training approaches).
- Evaluate the generated test cases in terms of correctness, coverage, usefulness, and practicality.
- Document the work and present results to the Ericsson team.
The skills you bring:
- Currently pursuing a master's degree in Computer Science, Software Engineering, AI/ML, or a related field.Interest in AI and its applications in engineering workflow.Some knowledge of MiniZinc or constraint programming is reqsuired.Comfortable working with code, experiments, and technical problem solving.Curious, self-driven, and willing to explore different approaches and compare results
- Interest in AI and its applications in engineering workflow.
- Some knowledge of MiniZinc or constraint programming is reqsuired.
- Comfortable working with code, experiments, and technical problem solving.
- Curious, self-driven, and willing to explore different approaches and compare results.
- Suitable for two candidates, 30 ECTS credits each.
Why join Ericsson?
At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply?
Click Here to find all you need to know about what our typical hiring process looks like.
Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city:
Sweden (SE) || Stockholm
Req ID:
775785
About this opportunity:
MiniZinc is widely used to model complex configuration and optimization problems, especially in telecom systems. These models can be very large, and creating good test cases for them is time-consuming and often done manually. With recent progress in Large Language Models (LLMs), there is now an opportunity to explore whether AI can help automate this process.
This thesis explores how LLMs can be used to generate test cases for MiniZinc models. The focus is on understanding how well AI can interpret constraints, produce inputs and output, and support testing. Different approaches, prompting strategies, and model setups can be investigated to understand what works best in practice. The results can help Ericsson evaluate the potential of AI-assisted testing for constraint-based systems.
What you will do:
- Review relevant research on AI for code generation, automated testing, and constraint programming.
- Study a large MiniZinc model and understand the structure and purpose of its key constraints.
- Develop and test methods for generating MiniZinc test cases using LLMs.
- Build a workflow where the LLM creates test cases and the MiniZinc solver checks them.
- Explore and compare different ways of using LLMs for this problem (e.g., different prompting strategies, workflows, or training approaches).
- Evaluate the generated test cases in terms of correctness, coverage, usefulness, and practicality.
- Document the work and present results to the Ericsson team.
The skills you bring:
- Currently pursuing a master's degree in Computer Science, Software Engineering, AI/ML, or a related field.Interest in AI and its applications in engineering workflow.Some knowledge of MiniZinc or constraint programming is reqsuired.Comfortable working with code, experiments, and technical problem solving.Curious, self-driven, and willing to explore different approaches and compare results
- Interest in AI and its applications in engineering workflow.
- Some knowledge of MiniZinc or constraint programming is reqsuired.
- Comfortable working with code, experiments, and technical problem solving.
- Curious, self-driven, and willing to explore different approaches and compare results.
- Suitable for two candidates, 30 ECTS credits each.
Why join Ericsson?
At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply?
Click Here to find all you need to know about what our typical hiring process looks like.
Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city:
Sweden (SE) || Stockholm
Req ID:
775785
Ericsson AB
FöretagEricsson AB
Visa alla jobb för Ericsson AB