Thesis Student - From Requirements to Proof: Exploring AI-Assisted Software Verification

Scania Latin America; Stjärna; On-site; SEK 167,000 - 234,000; Full time

Job summary

Scania is offering a thesis opportunity focused on AI-assisted software verification. You will translate requirements to formal properties and review specifications for verification, starting January 2027.

The work considers C++/Java in a formal verification context and explores SSD approaches with LLM support for automotive software. You will collaborate with thesis supervisors at Scania, contributing to a research-driven project with a clear evaluation path and potential impact on

Qualifications

• Currently pursuing a master's degree in Computer Science, Software Engineering, Computer Engineering, Embedded Systems, or related field.
• Experience with C, C++, or Java is helpful.
• Interest in AI and software quality is a plus.

Responsibilities

• Translate requirements into formal properties for verification.
• Review generated specifications before verification.
• Assess what the formal approach can prove and its limitations.
• Collaborate with supervisors and explore SSD for C++/Java.

Skills

C/C++

Java

AI

Education

Master's degree in CS/SE/CE

Job description

Select how often (in days) to receive an alert: Create Alert

This position is within one of TRATON’s companies.

Thesis Student - From Requirements to Proof: Exploring AI-Assisted Software Verification

From Requirements to Proof: Exploring AI-Assisted Software Verification- 30 Credits

Introduction

Interested in AI and software development? Explore how AI and logical reasoning could help check automotive software at TRATON. Apply your knowledge to a real engineering challenge and build connections for your future career.

Background

Large language models (LLMs) can generate code from written requirements, but that code still needs independent validation. Specification-driven development (SSD) makes requirements precise so verification tools can check whether the code meets them.

At TRATON, Software System Change Requests (SSCRs) describe software changes. With many supported configurations, testing every combination can be costly and may miss edge cases. Formal verification uses logical reasoning to check code against specified requirements across the configurations included in a model. This could reduce the need for configuration-specific unit testing.

Objective

Explore whether formal verification, supported by an LLM, can show that a selected SSCR implementation meets its requirements across modeled configurations, without running tests as part of the check.

Starting with one selected SSCR and related User Function(s), you will explore how an LLM can help translate requirements into formal properties: precise statements that verification tools can check against the code. You will review generated specifications before verification. Compilation and static analysis may support the workflow. Existing test results can provide a comparison, but will not form part of the formal proof. You will assess what the approach can prove, its limitations, its suitability for the selected code, and SSD support for C++ and Java.

Your profile

You are studying towards a master’s degree in Computer Science, Software Engineering, Computer Engineering, Embedded Systems, or a related field. You enjoy programming and are curious about AI and software quality. Experience with C, C++, or Java is helpful.

Number of students:1 or 2

Start date for the thesis work: January 2027

Estimated time required: June 2027

Contact persons and supervisors

Marcus Jakobsson, Thesis supervisor, [e-mail]