HPC Production Engineer
Jump TradingAbout the Role
Join Jump Trading Group's global High Performance Computing Team to design, implement, maintain, and support large-scale high performance compute and storage systems. You will work with compute, scheduling, networks, and large-scale data storage systems that support data pipelines and quantitative research. As a hands-on individual, you will leverage your deep expertise in Linux environments and software development to manage uniquely customized systems at scale, collaborate across teams on infrastructure optimization, and provide operational support to researchers leveraging HPC infrastructure.
Requirements
- 5+ years of professional experience in high performance computing (HPC), including parallel filesystems (e.g., Lustre, GPFS), batch systems (e.g., Slurm, Grid Engine), and high-performance network interconnects experience is a plus, but not required
- 5+ years of experience with Linux systems administration
- High proficiency with at least one programming/scripting language (e.g., Go, Python, C)
- Extensive experience designing, building, and maintaining complicated, interdependent, and distributed systems
- Extensive experience profiling and debugging application stacks (debuggers and profilers)
- Experience with system configuration management tools (SaltStack, Ansible, Puppet, etc.)
- A compulsion to perform root cause analysis
- Reliable and predictable availability
- Hands-on, highly skilled in the details and nuances of managing Linux environments with a strong software development background necessary to support uniquely customized systems at scale