We are looking for new collaborators for the following positions:
Scientific Software Developers
CSCS is leading an effort to develop HPC libraries and applications for heterogeneous HPC platforms. This work involves close collaboration with domain scientists and working on cutting edge HPC technologies, to ensure that scientists will be able to fully utilize HPC systems based on many-core architectures. To this end, CSCS has several positions open at our office at ETH in Zurich for Scientific Software Developers.
The main role of these positions is to develop software libraries for scientific computing, specifically performance-portable C++ libraries for multi-core and many-core HPC architectures. The position will also require working closely with application developers and domain scientists to use the libraries into their applications. The positions are funded by a project, so we can offer two-year contracts for the length of the project. The positions will be at ETH Zurich, with regular travel to CSCS offices in Lugano. The starting date is January 2017, or as soon as possible thereafter.
The mission of the Scientific Computing Support Unit is to enable scientists from all computational domains to make the most efficient use of CSCS leading-edge supercomputing resources. This unit is responsible to build bridges between the user and various units at CSCS, at a larger scale also among the various Swiss computational research communities.
In order to strengthen our team we are seeking a Computational Scientist.
In this exciting and stimulating role you will be entrusted with a variety of responsibilities, your main focus will be the implementation and maintenance of our scientific software deployment strategy. Your challenge is to assure that the applications are always yielding the best possible results on our leading-edge HPC systems, on production and also through system interventions (such as the upcoming major upgrade of Piz Daint). In addition, you will be able to use your knowledge of HPC and accelerators (GPU, Xeon Phi) to interface with international researchers, in order to provide first and second level support for our portfolio of scientific applications and libraries. Your knowledge of collaborative development tools (such as Github) will enable you to apply continuous integration/validation techniques to unique and large scale systems.
Applicants should have a Ph.D. preferably in Computer Science with a background in parallel computation. Demonstrated experience with numerical libraries, performance optimization and I/O in scientific applications. Know-how of code development tools such as IDEs, debuggers, performance and monitoring tools is a must.