Master Thesis: AI-driven Test Failure Root Cause Analysis
Ericsson • Linköping, Sweden
-
Role & seniority
-
Thesis / project role focused on ML/LLM for software test failure analysis
-
Seniority: student thesis (Master’s level)
-
-
Stack/tools
-
Cloud/data: AWS S3 (CI/CD test data)
-
LLMs: LLaMA-3, Mistral, GPT variants (as applicable)
-
Compute/engineering: build/CI/CD integration (test metadata/features)
-
-
Top 3 responsibilities
-
Build a Test Failure Root Cause Assistant using CI/CD historical data and ML/LLMs
-
Analyze and infer root causes across unit, integration, and system test stages
-
Develop models to classify failure types and/or recommend root causes using features like flakiness and build metadata
-
-
Must-have skills
-
Master’s student in computer science/computer engineering or similar
-
Background in software testing
-
Background in AI/ML (preferred)
-
-
Nice-to-haves
-
Experience with LLM-based systems and/or model training/classification
-
Familiarity with CI/CD test analytics (test suite duration, smell types, commit frequency, environment features)
-
-
Location & work type
-
Location: Sweden (SE), Linköping
-
Work type: thesis/project (on-site implied; not explicitly stated as remote)
-
Full Description
Join our Team
About this opportunity
Software testing is a cornerstone of high-quality software delivery. However, test failures, especially those without clear root causes, lead to productivity loss, slow release cycles, and unreliable systems. This thesis investigates the use of Machine Learning (ML) and Large Language Models (LLMs) to analyze test failures and provide root cause insights across various testing stages (unit, integration, system), using data already collected from CI/CD pipelines and stored in S3.
What you will do
This thesis project revolves around building a Test Failure Root Cause Assistant powered by
Existing CI test data (stored in AWS S3) Large Language Models like LLaMA-3, Mistral, or GPT variants Metadata & features such as commit frequency, test flakiness, smell types, test suite duration, and build environment Engineer features across multiple test levels (unit/integration/system). Train models to classify test failures or recommend root causes.
The skills you bring
Master´s student in computer science, computer engineering, or similar. Background in software testing and AI/ML is preferred.
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: 791417
