HPC Operations Engineer – High-Performance Infra & Automation

Evergreen Statistical Trading; Bellevue (WA); On-site; USD 170,000 - 230,000; Full time

Benefits offered by this job

Signing bonus

Performance bonus

Company-paid medical benefits

Job summary

Evergreen is a proprietary trading firm based in Bellevue, Washington. As an HPC Operations Engineer, you will own the day-to-day operation of our research clusters across multiple datacenters and the scheduled workloads that our research and trading operations depend on.

You will work on a modern, legacy-free tech stack and take on large projects across software and hardware as our HPC footprint expands, including ownership of critical processes and deep collaboration with the datacenter team.

Qualifications

• Strong hands-on Linux systems administration experience, particularly with Red Hat-family distributions such as RHEL, Rocky Linux, AlmaLinux, etc.
• Strong proficiency with Python for automation and tooling
• Experience with version control tools, ideally Git, as well as versioned configuration management
• Experience with monitoring and alerting systems, ideally Prometheus and Grafana
• Experience with batch schedulers, ideally Slurm, including queue configuration, resource management and troubleshooting
• Experience with cluster provisioning tools such as Warewulf, xCAT, etc.
• Experience with ZFS and parallel filesystems such as GPFS, Lustre, etc.
• Experience with InfiniBand networking
• Ability to own critical processes, design them not to break, and resolve critical issues outside of business hours
• Ability to direct hardware work through datacenter remote hands, and be hands-on when the situation calls for it
• Ability to diagnose complex problems in production systems under time pressure
• Growth-oriented and collaborative mindset; enjoys working within a team
• Passion for high-performance infrastructure that runs correctly and with minimal drama

Responsibilities

• Own the day-to-day operation of our research clusters across multiple datacenters
• Manage scheduled workloads our research and trading operations depend on
• Work on a technology stack unencumbered by legacy infrastructure
• Tackle substantial projects across both software and hardware as HPC footprint expands

Skills

Linux system administration

Python programming

team collaboration

problem solving

ownership of critical processes

Tools

Git

Prometheus

Grafana

Slurm

Warewulf

xCAT

ZFS

Lustre

InfiniBand

Job description

Evergreen is a proprietary trading firm based in Bellevue, Washington. As an HPC Operations Engineer, you will own the day-to-day operation of our research clusters across multiple datacenters and the scheduled workloads that our research and trading operations depend on.

You will work on a modern, legacy-free tech stack and take on large projects across software and hardware as our HPC footprint expands, including ownership of critical processes and deep collaboration with the datacenter team.