Scientific Employee (f/m/d)

Zuse-Institut Berlin; Berlin; On-site; EUR 42,000 - 56,000; Full time

Job description

Position Details

For the Algorithms for Innovative Architectures workgroup of the Distributed Algorithms and Supercomputing department, we are offering this position, starting as soon as possible, on a full-time basis (39,4 hours per week), limited until March 31, 2029. If the applicant meets the relevant wage requirements and personal qualifications, the salary will be based on remuneration group 13 TV-L of the pay scale for the German public sector.

Background & Context

The position is embedded in the HPCLab of Research Campus MODAL, a public–private research partnership involving the Zuse Institute Berlin (ZIB) and Freie Universität Berlin. MODAL develops mathematical methods and digital decision-support systems for data-intensive modelling, simulation and optimisation in areas such as energy, health and mobility. Within this interdisciplinary setting, the HPCLab develops algorithmic and software solutions to run data-driven optimisation and simulation workflows efficiently on emerging high-performance computing architectures, including heterogeneous processors, high-speed networks and modern storage systems.

Your Tasks

• Porting and adaptation of representative scientific simulation codes and AI workloads to modern computing architectures, including NextSilicon's Maverick-2 dataflow accelerator, GPUs and emerging CPU architectures such as RISC-V, with FPGA implementations where appropriate
• Evaluation of the performance and energy efficiency of the resulting ports and platforms using application-specific benchmarks
• Analysis of network topologies and use of programmable NIC capabilities for representative AI workloads on modern HPC interconnects, including InfiniBand and Cornelis Networks' Omni-Path, as well as emerging fabrics for HPC and AI
• Optimization of the next-generation Omni-Path interconnect to support the DAOS HPC object store for MODAL-relevant application patterns, and evaluation of the performance of its native key-value store
• Preparation and presentation of research findings for publication at peer-reviewed international conferences and in scientific journals
• Contributions to the group's open-source codebases, including testing and documentation

Your Profile

• A university degree (Master's or Diplom) in computer science, mathematics, or a related subject
• Knowledge of computer architectures, accelerators, networks, and data management systems
• Programming experience, preferably in C, C++, Fortran, and Python, and routine use of Linux, including the command line
• A strong interest in new research questions, their solution, and the practical implementation of research results
• A high degree of independence and commitment, as well as the ability and willingness to prepare and publish scientific work for an international audience
• Very good spoken and written English, and a collaborative working style

Ideally, you also have:

• Experience with GPU-accelerated programming
• Familiarity with Git-based collaborative development and code review

What you can expect

We offer a friendly work environment with flexible work and meeting times, excellent equipment and a challenging professional environment as well as

• comprehensive training in a competent and cooperative team,
• professional training opportunities and support in professional development,
• an additional pension scheme (VBL),
• 30 days annual leave, flexible working hours (flexitime),
• a salary based on TV-L (collective agreement for the public service of the federal states) in accordance with qualifications and professional experience with annual bonus payment,
• capital allowance of up to € 150 per month, or alternatively a BVG job ticket plus the remaining balance,
• the use of canteens and sports programs of the Freie Universität Berlin (FUB) at reduced rates.

The Zuse Institute Berlin is committed to diversity, equal opportunities, and a respectful and inclusive working environment. In order to increase the proportion of women in areas where they are underrepresented, we expressly encourage women to apply. Irrespective of this, we welcome applications from all qualified candidates regardless of age, disability, ethnic or social background, religion or belief, sexual orientation, or gender identity.

Our private policy statement regarding application data is available at www.zib.de/impressum.

For further job offers please visit our website at https://zuse-institut-berlin.jobs.personio.de/.

Contact

For further information about the position, please refer to our website www.zib.de or contact Dr. Florian Schintke ([e-mail]).