Automatic Test Generation with Symbolic Execution Engines and LLM Powered Tools for C and C++ Programs (exjobb)

The opportunity:

We are looking for a master thesis student at our R&D department, would like to join our multinational organization with lots of development opportunities. Our team is dedicated to creating a future where innovative digital technology brings cleaner energy to people around the world. If this opportunity excites you, we encourage you to apply!

Unit testing is an integral part of ensuring software quality. Achieving sufficient code coverage with manually written unit tests is time-consuming and not guaranteed to identify all edge cases. Automatic test generation tools based on symbolic execution have been developed to address this gap. KLEE is one such tool built on top of the LLVM infrastructure and works with programs compiled for the LLVM virtual instruction set. However, for programs built using different compilers, such as MSVC and GCC, using KLEE for automated test generation remains challenging. Recently, LLM-based tools such as GitHub Copilot and Azure OpenAI-powered assistants have demonstrated their capabilities in software development environments but come with disclaimers due to their inherent probabilistic approaches.

How you'll make an impact:

• Harness the power of large language models (LLMs) to generate intelligent unit tests and compare their effectiveness against symbolic execution strategies.
• Build a practical toolchain that converts symbolic execution artifacts into Google Test-compatible unit tests, including scaffolding, harnesses, and test doubles.
• Define and apply performance metrics-such as coverage, bug-finding rate, and computational cost-to benchmark symbolic, LLM-based, and hybrid approaches.
• Contribute to empirical research and publish findings that guide developers in choosing the most effective test generation strategy for their pipelines.
• Work hands-on with open-source and proprietary projects to validate your solutions in diverse, real-world scenarios.
• Shape the future of software quality assurance by delivering actionable insights and reusable tools for the developer community.
• Living Hitachi Energy's core values of safety and integrity means taking responsibility for your own actions while caring for your colleagues and the business.

Your background:

• Bachelor's degree in computer science, Software Engineering, or a related field.
• Proficiency in C/C++ and Python; familiarity with LLVM/clang toolchain.
• Experience with symbolic execution (KLEE) and unit test frameworks (Google Test).
• Understanding coverage tooling (llvm-cov, gcov/lcov) and sanitizers (ASan/UBSan).
• Familiarity with LLM-based coding assistants and prompt engineering best practices.

More about us:

Are you ready for an exciting new challenge? Does the above description sound like you? Applications will be reviewed on an ongoing basis, so don't delay - apply today! Recruiting Manager: Lucas Bottura, lucas.botura@hitachienergy.com and thesis supervisor: Mohammed Shaik, mohammed-salman.shaik@hitachienergy.com will answer your questions about the position.

Don't hesitate - apply today and let us learn more about you and the unique contributions you can bring to our team.

Apply now

Current employees apply here

Client-provided location(s): Västerås, Sweden, Ludvika, Sweden

Job ID: Hitachi_Energy-JID3-157777

Employment Type: PART_TIME

Posted: 2025-10-01T23:34:59