Senior/ Research Scientist (High Performance Computing Branch)

[What the role is]
The Centre for Climate Research Singapore (CCRS) is a division of the Meteorological Service Singapore (MSS). At CCRS, our mission is to advance scientific understanding of tropical climate variability and change and its associated weather systems affecting Singapore and the wider Southeast Asia region, so that the knowledge and expertise can benefit decision makers and the community. Our vision is to be a world leading centre in tropical climate and weather research focussing on the Southeast Asia region.

Within CCRS, the High Performance Computing (HPC) Branch is responsible for the technical development, optimization, implementation and management of CCRS’s software systems running on in-house ‘Utama’ and Singapore National Supercomputing Centre (NSCC) HPC systems. CCRS’s core ‘SINGV’ weather/climate modelling system is a regional, tropical configuration of the Unified Model (UM), used in both weather (Numerical Weather Prediction – NWP) and climate change (regional climate projections) applications. CCRS is also enhancing its rainfall nowcasting capabilities (predicting heavy rainfall in Singapore over the next 30-60 minutes) using machine learning techniques in collaboration with local and international partners. Applications of AI across the weather and climate science domain on large HPCs will be an increasing focus for the HPCB in coming years.
As part of the HPC Branch, the postholder will contribute to the technical development, optimisation, operational implementation, and management of CCRS' core modelling systems running on CCRS in-house and off-premise Linux-based HPC systems.

[What you will be working on]

The job scope will include but not limited to the following:

• Manage and maintain CCRS core modelling system (Unified Model) code, suites, and software tools
• Configure and implement operational NWP systems and suites, optimising for GPU-/CPU-based HPC architectures
• Monitor and troubleshoot the production of operational NWP systems on HPC platforms
• Collaborate on modelling software development with external partners

[What we are looking for]

The job might be for you if you possess the following:

• Degree, Master’s or PhD in physical, computational or data science, or related field
• 3+ years of scientific software development on HPC systems
• Proficiency in scientific programming languages (Python, Fortran, UNIX shell scripting, C/C++)
• Experience with UNIX/Linux-based supercomputer/server administration, preferably including HPE/Cray system
• Familiarity with data transfer protocols and large dataset management
• Experience with Rose/Cylc Workflow Engine, containerisation, or machine learning
• Familiarity with Subversion and/or Git
• Experience designing environmental modelling workflows
• Knowledge of system administration on HPE/Cray HPC system and software

As part of the shortlisting process for this role, you may be required to complete a medical declaration and/or undergo further assessment.

Applicants will be updated on the status of their applications within 4 weeks of the closing date of this job posting.