HPC Systems Administrator | Experienced Hire

Susquehanna International Group, LLP; Bala Cynwyd (PA); On-site; USD 120,000 - 180,000; Full time

Job summary

Susquehanna International Group, LLP (SIG) seeks an experienced HPC Engineer to build and optimize the systems powering our trading and research workloads. You’ll manage GPUs, CPU clusters, and petabytes of storage supporting hundreds of researchers worldwide.

The role emphasizes automation with Python and Bash, collaboration with researchers and IT teams, kernel and I/O tuning, and comprehensive HPC environment management including schedulers, filesystems, and interconnects.

Qualifications

• Bachelor’s degree in Engineering, CS, Information Systems, or related field (or equivalent).
• Experience building and operating Linux-based HPC platforms.
• Experience tuning kernel and I/O subsystems; perf tools like perf, strace, tcpdump, Wireshark.

Responsibilities

• Automate and evolve home-grown tools with Python and Bash to monitor and maintain HPC systems.
• Collaborate with Strategy Developers, Quant researchers, and trade-supporting teams to translate problems into scalable solutions.
• Optimize operating systems and batch workflows for performance; perform root-cause analysis of failures.
• Oversee all aspects of our HPC environment, including the scheduler, parallel filesystems, GPUs, and interconnects.
• Implement and optimize high-performance storage solutions (Lustre, VAST, GPFS) to support cluster performance.
• Troubleshoot and tune to ensure timely recovery of disrupted workflows.

Skills

Python

Bash

Automation

Linux HPC

Education

Bachelor's degree in Engineering, CS, Information Systems, or related field

Tools

Ansible

Lustre

GPFS

VAST

Slurm

Wireshark

Job description

Overview

As a member of our HPC team, you’ll build and optimize the systems that power our trading and research, from high-performance trading infrastructure and compute clusters to databases and support tooling. You’ll manage an environment of thousands of GPUs, hundreds of thousands of CPU cores, and hundreds of petabytes of storage, serving over 100 quantitative researchers and scientists worldwide.

What You’ll Do:

• Automate and Evolve:Contribute to our library of home-grown tools, written primarily inPython and Bash,to automate monitoring, and maintenance, allowing you to focus on performance related issues and projects.
• Collaborate:Work closely with Strategy Developers, Quantitative Researchers, and trade-supporting application teams to translate complex problems into scalable solutions. Coordinate with IT infrastructure teams, including storage and networking, to identify and implement the best solutions.
• Optimize:Tuneoperating systemsandbatch workflowsfor performance. Dive deep onroot-cause analysisof systems issues. Integrate all of these solutions into our systems effectively and efficiently.
• Comprehensive HPC Environment Management :Oversee all aspects of our HPC environment, including the scheduler, parallel filesystems, GPUs, and interconnects.
• High throughput storage :Implement and optimize high-performance storage solutions, including Lustre, VAST, and GPFS, to efficiently support and enhance cluster performance.
• Capacity Planning and Design :Develop strategies to ensure optimal resource allocation and scalability, using analytics to forecast needs and design efficient, reliable systems.
• Troubleshooting and Tuning :Utilize monitoring and diagnostic tools to quickly pinpoint failures, streamline troubleshooting processes, and ensure the timely recovery of disrupted workflows.

What we’re looking for

• Bachelor’s degree in Engineering, Computer Science, Information Systems, or a related field (or equivalent experience)
• Experience building and operating Linux-based HPC platforms
• Experience tuning kernel and I/O subsystems and troubleshooting performance with tools such as sysctl, perf, strace, tcpdump, and Wireshark
• Strong automation skills in Python, Bash, or configuration management tools such as Ansible
• Experience administering parallel filesystems such as Lustre, GPFS, or VAST
• Experience administering and tuning workload schedulers such as Slurm
• Familiarity with high-speed interconnects (InfiniBand, RoCE) and GPU cluster environments

About Susquehanna

Susquehanna is a global quantitative trading firm powered by scientific rigor, curiosity, and innovation. Our culture is intellectually driven and highly collaborative, bringing together researchers, engineers, and traders to design and deploy impactful strategies in our systematic trading environment. To meet the unique challenges of global markets, Susquehanna applies machine learning and advanced quantitative research to vast datasets in order to uncover actionable insights and build effective strategies. By uniting deep market expertise with cutting-edge technology, we excel in solving complex problems and pushing boundaries together.

#LI-AM1

#LI-Onsite