Start Date
Immediate
Expiry Date
22 Oct, 25
Salary
0.0
Posted On
22 Jul, 25
Experience
0 year(s) or above
Remote Job
Yes
Telecommute
Yes
Sponsor Visa
No
Skills
Computer Science, English, Mathematics, Tor, Machine Learning, Data Science
Industry
Information Technology/IT
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.
In their day-to-day development, SAP HANA developers investigate issues of the SAP HANA Cloud Database by reading logs, traces, and crash dumps. Due to the large size of the SAP HANA C++ code base, faults can occur in locations not immediately known to developers. The SAP HANA Fault Localization workstream fine-tunes a large language model which determines the root cause of faults from SAP HANA traces to automate program repair activies and save human time.
In this project you design and run experiments to analyze the performance of our machine learning pipeline, integrate improvements based on your insights, and measure their effect to increase our accuracy. The pipeline is written in Python and makes use of PyTorch, transformers, and matplotlib.
Besides having the possibility to join our team as a working student or an intern, we also provide you with the opportinity to do so as a thesis student!