HPC Systems Engineer
Jump Trading is a global trading firm where traders, engineers, and researchers develop trading strategies, models, infrastructure, and systems across asset classes and time horizons.
About Jump Trading
Jump Trading is a global trading firm focused on research-driven trading and the engineering of scalable models, tools, infrastructure, and execution systems. Its operations combine trading, technology, AI/ML, and quantitative research, and it also runs research and talent programs including conference travel grants and a fellowship program.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will design, implement, maintain, and support high-performance compute and storage systems in a production environment. You will monitor infrastructure, build software deployment tooling, collaborate with researchers and engineers, provide operational support, manage vendor relationships, and optimize HPC resources.
Requirements
- 5+ years of professional high-performance computing experience
- Parallel filesystems
- Lustre
- GPFS
- Batch systems
- Slurm
- Grid Engine
- Linux systems administration
- Go
- Python
- C
- Distributed systems
- Profiling
- Debugging
- Configuration management
- SaltStack
- Ansible
- Puppet
- Root cause analysis
- Reliable and predictable availability
Responsibilities
- Design high-performance compute and storage systems
- Implement performance and fault monitoring systems
- Monitor systems storage and network performance
- Build software and operating system deployment tooling
- Write code and testing infrastructure
- Develop systems and user documentation
- Participate in coordinated maintenance operations
- Optimize researchers' use of HPC infrastructure
- Provide rotating operational support
- Manage vendor relationships
- Perform root cause analysis