ETH Zurich is one of the world’s leading universities specialising in science and technology. It is renowned for its excellent education, its cutting-edge fundamental research and its efforts to put new knowledge and innovations directly into practice.
The Federal Institute of Meteorology and Climatology MeteoSwiss and the Scalable Parallel Computing Lab of ETH are involved in a project to adapt complex numerical weather and climate simulation models to accelerators such as NVIDIA GPUs and Intel Xeon Phi. As a result of several projects within the PASC initiative, a weather and climate model was successfully ported to graphics processing units (GPUs) achieving a significant speedup with respect to the CPU code. To join the interdisciplinary team, we are offering two positions for a
Scientific Software Engineer / Developer (100%)
Your task will be to contribute to the implementation of a new weather and climate model using modern C++ and a domain-specific language (DSL) programming model. Further, you will help design and implement next-generation programming models and optimized backends for the weather and climate modelling domain. You will join a team developing compiler technology aiming to provide performance portability across multiple architectures while retaining a programming model with a high level of abstraction.
We offer an engaging position which provides the opportunity to work on leading edge software and hardware technologies in the high-performance computing field, to collaborate with internationally renowned research groups and supercomputing centres, and to develop production quality software. You will be part of a motivated and goal-driven team. We offer an internationally competitive salary (based upon qualifications and experience).
The successful candidate has a degree in Computer Science, Computational Science or a related field with outstanding programming skills in C++ and have sound experience in high-performance computing and parallel programming. You have solid experience with C++11 and GPU programming using CUDA programming model. Experience with STL and Boost libraries is also a must. Interest and experience in Fortran, high-performance computing, numerical simulations and/or weather or climate modelling are considered an advantage. To round off your profile, you are a team-oriented and goal-driven individual and enjoy working in a diverse working environment.
The positions are available as of April 2019 (or as soon as possible thereafter). Initial appointment is for one year. The working place is at MeteoSwiss (Zurich airport, easily accessible by public transport), but will involve strong interaction with the Scalable Parallel Computing Lab and the Swiss National Supercomputing Centre.