JobbSafariLediga jobbMaster Thesis: Evaluating AI-Generated Alternatives to Open-Source Dependencies
Master Thesis: Evaluating AI-Generated Alternatives to Open-Source Dependencies
Ericsson ABNy
Sammanfattning
This opportunity involves a thesis project focused on investigating whether AI-generated code can effectively replace third-party dependencies in software development. Located in Linköping, Sweden, the role includes conducting research on AI code generation, building a toolchain for library interface extraction, and evaluating the quality of AI-generated replacements. The findings will culminate in a decision framework for the Ericsson team regarding the responsible use of AI in dependency code.Det här erbjuder vi
Opportunity to work on innovative solutions to complex problems.Collaborative environment with a diverse team of innovators.Encouragement of diverse and inclusive practices within the organization.
Ansök senast: Öppet tillsvidare
Publicerad: 2026-09-25
Beskrivning
Join our Team
About this opportunity:
Modern software products are assembled from hundreds of third-party open-source components, and each one carries a cost for the lifetime of the product: license review, SBOM tracking, continuous vulnerability monitoring, forced upgrades, and the risk of abandonment. Yet an application typically uses only a small fraction of the interface a library exposes, while inheriting the obligations for all of it. As AI coding agents become capable of implementing well-specified functionality, it is worth asking whether importing a dependency is still the right default.
This thesis investigates experimentally whether AI-generated code can replace third-party dependencies, and when doing so is a sound engineering decision.
What you will do:
The work concludes with a decision framework indicating when, and for which kinds of dependency, replacement by AI-generated code is a responsible choice, presented to the Ericsson team.
The skills you bring:
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) || Linköping
Req ID: 791415
About this opportunity:
Modern software products are assembled from hundreds of third-party open-source components, and each one carries a cost for the lifetime of the product: license review, SBOM tracking, continuous vulnerability monitoring, forced upgrades, and the risk of abandonment. Yet an application typically uses only a small fraction of the interface a library exposes, while inheriting the obligations for all of it. As AI coding agents become capable of implementing well-specified functionality, it is worth asking whether importing a dependency is still the right default.
This thesis investigates experimentally whether AI-generated code can replace third-party dependencies, and when doing so is a sound engineering decision.
What you will do:
- Survey research on AI code generation and dependency management and define how a generated replacement should be judged against the original library.
- Build a toolchain that extracts a library's public interface, has an AI agent implement a replacement for it, and compares the result against the original.
- Evaluate correctness, security including the library's known vulnerability history, and other relevant qualities across libraries with differing characteristics.
The work concludes with a decision framework indicating when, and for which kinds of dependency, replacement by AI-generated code is a responsible choice, presented to the Ericsson team.
The skills you bring:
- Master's student in computer science, software engineering, cybersecurity, or related field.
- Strong background in programming.
- Experience with software testing and static analysis (preferred).
- Familiarity with AI/LLM tooling (useful but not required).
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) || Linköping
Req ID: 791415
Ansök till tjänsten
Master Thesis: Evaluating AI-Generated Alternatives to Open-Source Dependencies
Ny
OM FÖRETAGET
Ericsson AB
