Software Engineer
We help the world run better At SAP, we enable you to bring out your best.
We help the world run better
At SAP, we enable you to bring out your best. Our company culture is focused on collaboration and a shared passion to help the world run better. How? We focus every day on building the foundation for tomorrow and creating a workplace that embraces differences, values flexibility, and is aligned to our purpose-driven and future-focused work. We offer a highly collaborative, caring team environment with a strong focus on learning and development, recognition for your individual contributions, and a variety of benefit options for you to choose from.
What you'll build
In their day-to-day development, SAP HANA developers review code changes generated by AI coding agents. These changes must meet high quality standards before they can be merged into production code.
Today, we verify that AI-generated code passes determistic verification (e.g. linting, tests) but we don’t yet measure whether changes fulfill other criteria (e.g code conventions). This can lead to a lower acceptance of AI-generated changes.
In this project you design and run experiments to evaluate an automated quality evaluation system that uses large language models and techniques like LLM-as-a-Judge to assess AI-generated changes. You build a ground-truth dataset from real developer review feedback, design a structured scoring rubric, and benchmark how well an LLM judge correlates with human decisions. The project is implemented in Python and makes use of modern coding agents like Cline and Claude Code, statistical analysis, and experiment tracking with MLflow.
What you bring
Expected qualifications:
The application must contain (English or German):
Where you belong
Join a team that values creativity, encourages risk-taking, and counts on your unique ideas. Our goal is to build and maintain a state-of-the-art agentic AI coding platform for SAP HANA.
Posted July 22, 2026