Master Thesis: AI Agents to Enhance Test Intelligence
Ericsson • Linköping, Sweden
-
Role & seniority
-
Thesis/early research role to design and prototype an AI-powered test data assistant
-
Seniority: Student/entry (Master’s thesis level)
-
-
Stack/tools
-
LLMs (e.g., ChatGPT, LLaMA, Falcon)
-
AI/ML techniques
-
CI/CD test data stored in cloud storage (Amazon S3)
-
Interface: chat and/or dashboard (implied)
-
-
Top 3 responsibilities
-
Prototype an assistant that ingests and reasons over stored CI/CD test data
-
Enable natural-language use cases (e.g., failure diagnostics, unstable tests, coverage gaps, failure summaries)
-
Support stakeholder Q&A across testing loops (unit, integration, system) using historical data
-
-
Must-have skills
-
Master’s student in CS/EE/Computer Engineering or similar
-
Proficiency in AI, machine learning, and LLMs
-
-
Nice-to-haves
-
Experience with test analytics, automated testing, or handling large-scale test datasets
-
Experience building LLM applications with data from systems like CI/CD and S3
-
Familiarity with natural-language interfaces (chat/dashboard)
-
-
Location & work type
-
Sweden (SE), Linköping
-
On-site/Local to the thesis placement (work type: thesis/prototype project)
-
Full Description
Join our Team
About this opportunity
Modern software development relies heavily on automated testing at various levels such unit, integration, and system. In many large-scale projects, vast amounts of test data are collected continuously through CI/CD pipelines and stored in cloud storage systems like Amazon S3. However, most of this data remains underutilized, especially in helping stakeholders like testers, developers, test managers, and system test engineers understand, analyze, and improve test outcomes. With the rapid advancement in Large Language Models (LLMs) (e.g., ChatGPT, LLaMA, Falcon), there is now an opportunity to create AI-powered assistants that can ingest and reason over this data to support
Test failure diagnostics Coverage gaps Natural-language Q&A on test history from different loops like unit testing, integration testing and system testing Generating test documentation or summaries
What you will do
The goal of this thesis is to design and prototype an AI-powered assistant using stored test data and LLMs to support test related stakeholders in large-scale systems. The assistant should enable natural interactions (via chat or dashboard) and answer queries such as
Why did this test fail last week? Which test cases are most unstable? What are common reasons for integration test failures? Summarize failures from the last 3 builds.
The skills you bring
Master´s student in electrical engineering, computer science, computer engineering or similar. Proficiency in AI, machine learning, and LLMs
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: 791416
