HPC Systems Engineer
Jump Trading22 days ago
Mumbai, IndiaSenior
Responsibilities
- Design, implement, maintain, and support high-performance compute and storage systems.
- Implement and support performance-monitoring and fault-monitoring systems.
- Monitor compute, storage, and network performance.
- Build tooling to compile, package, install, and upgrade software and operating-system components at scale.
- Write code and testing infrastructure across new and existing codebases in multiple programming languages.
- Develop systems and user documentation.
- Participate in coordinated maintenance operations, including evenings and weekends.
- Collaborate with researchers to optimize their use of HPC infrastructure.
- Develop and monitor tools used to maintain production computing environments.
- Provide rotating operational support.
- Manage relationships with external vendors and travel domestically and internationally as needed.
- Follow company cybersecurity and IT policies and use only approved hardware and software.
Requirements
- At least 5 years of professional high-performance computing experience, including parallel filesystems and batch systems.
- At least 5 years of Linux systems administration experience.
- High proficiency in at least one programming or scripting language such as Go, Python, or C.
- Extensive experience designing, building, and maintaining complex, interdependent, distributed systems.
- Extensive experience profiling and debugging application stacks using debuggers and profilers.
- Experience with configuration-management tools such as SaltStack, Ansible, or Puppet.
- Strong root-cause-analysis orientation and reliable, predictable availability.
- Experience with high-performance network interconnects is a plus but not required.
Benefits
- Sydney office location.
- Rotating operational support and coordinated maintenance may include evenings and weekends.
- Domestic and international travel may be required for vendor meetings.
- Global infrastructure projects and collaboration with researchers and teams.