Master Thesis, Internship
Publication date:
10 October 2024Workload:
100%- Place of work:Zurich
Master Thesis, Internship
Internship or Master Thesis in graph theory and in developing libraries to enable powerful functional and executable graphs
Ref. 2024_020
Project description
A master’s student or intern position is available for a candidate interested in graph theory and in developing libraries to enable powerful functional and executable graphs. Graphs have a wide range of properties such as direction, cyclicity, edge weight, etc. which make them applicable to a wide range of domains including computer science, linguistics, chemistry, biology, etc. Many works propose powerful new algorithms for operating on graphs; however, such works usually consider their novelties in isolation, not tied to a pre-existing graph library.
In the IBM Analog AI team, we are developing architectures and methods for implementing Deep Neural Networks (DNNs) on Analog In-Memory Computing (AIMC) accelerators. AIMC platforms utilize non-volatile in-memory computing to perform extremely low energy and latency DNN inference. While promising for enabling low-power DNN execution from the cloud down to the edge, these highly heterogeneous accelerators present novel challenges in efficiently mapping the DNN onto the hardware. Our team is developing the tools necessary to accomplish these tasks, with part of this work developing a powerful functional graph library.
As part of our team, you will collaborate closely with researchers on identifying, developing, and integrating graph algorithms into our existing research efforts on AIMC Architectures. The work will involve developing the extensions for publication in a top-tier conference. The duration of the internship is at a minimum of 4 months and can be conducted either as a Master's thesis or as an internship.
Minimum Qualifications:
- Bachelor’s degree in computer science or machine learning, including equivalent practical experience
- Outstanding C++ programming skills, Python also beneficial
- Independent learning/working abilities
- Strong work ethic
Preferred Qualifications:
- Previous work with graphs, Boost Library
- Previously published / contributed to work in conference or journal venue
Diversity
IBM is committed to diversity at the workplace. With us you will find an open, multicultural environment. Excellent flexible working arrangements enable all genders to strike the desired balance between their professional development and their personal lives.
How to apply
Please submit your application through the link below. This position is available starting Spring 2025.
Contact
IBM Research GmbH