HPC Interconnect Specialist (f/m/d)

Leibniz-Rechenzentrum der Bayerischen Akademie der Wissenschaften; Garching bei München; On-site; EUR 65,000 - 90,000; Full time

Benefits offered by this job

60% mobile work for suitable tasks

Free parking

VBL pension plan

State-of-the-art work equipment

Discounted gym membership

Job summary

Leibniz-Rechenzentrum der Bayerischen Akademie der Wissenschaften is seeking an HPC Interconnect Specialist to join the HPC Systems Operation group in Germany. You will maintain high-speed interconnects, optimize MPI workloads, and ensure low latency across LRZ's national and state-wide clusters.

The role requires substantial HPC experience, Linux proficiency, and strong collaboration with cross-functional teams.

Qualifications

• Master's degree in computer science, mathematics, or natural sciences.
• At least three years of experience in high-performance computing.
• Hands-on expertise with HPC interconnects and MPI implementations.
• Solid Linux administration and scripting with Shell/Python.

Responsibilities

• Operate, maintain, and optimize high-speed interconnects for HPC clusters.
• Monitor fabric health, diagnose link errors, and resolve bottlenecks.
• Run benchmarks and characterize interconnect performance.
• Collaborate with system administrators, storage engineers and apps teams.

Skills

HPC interconnects

MPI

Linux

C/C++

Shell/Python

German/English

fault isolation

performance tuning

team collaboration

Education

Master's degree in CS/Math/Nat Sci

Job description

Description:

Looking for an employer you can count on? Join us!

HPC Interconnect Specialist (f/m/d)

Your Role and Responsibilities:

We are looking for an HPC Interconnect Specialist to join our HPC Systems Operation group. You'll be responsible for the day-to-day operation, maintenance, and optimization of the high-speed interconnects underpinning our HPC clusters — ensuring the lowest possible latency and highest throughput for MPI workloads, distributed storage, and large-scale parallel applications. These HPC clusters comprise the national supercomputer at LRZ as well as additional state-wide HPC clusters of various size.

• Deploy, configure, and manage network switches, fabric management software, and host-software stacks.
• Monitor fabric health, diagnose link errors, and resolve performance bottlenecks.
• Run benchmarks and characterize the interconnect performance.
• Tune network performance for MPI, distributed file systems, and storage traffic.
• Collaborate with HPC system administrators, storage engineers, and application teams to optimize end-to-end data paths.
• Evaluate and recommend new interconnect hardware and technologies.
• Hunt and fix bugs, often in collaboration with vendor companies.
• Maintain detailed network topology documentation.
• You actively contribute to the development and implementation of certified and transparent processes.

Your Qualifications:

• University degree (master or above) in computer science, mathematics, or natural sciences
• At least three years of experience in high-performance computing
• Deep hands-on expertise with various HPC interconnects
• Experience with various flavors of the Message-Passing Interface
• Understanding of MPI communication patterns and how they interact with the network layer
• Solid Linux administration skills
• Proficiency with compiled programming languages (e.g. C, C++)
• Proficiency in scripting and automation (e.g. Shell, Python)
• Analytical mindset with a structured approach to fault isolation and performance tuning
• Excellent German and English in writing and speaking
• You like to share your experience and review existing processes to identify opportunities for improvement within the team.

Of course, we provide comprehensive onboarding for career starters and professionals returning to the workforce.

Preferred Qualifications:

• Familiarity with GPU-to-GPU communication
• Knowledge of parallel file system networking
• Strong troubleshooting skills
• Ability to develop and implement practical solutions autonomously as well as in a team
• Service-oriented attitude

Conditions:

Working time

full time (40 hrs)

flexible working model with electronic time recording

Contract duration

24 months, a further employment is intended

Remuneration

up to E 13, seeEntgelttabelle TV-L

Annual leave / compensatory time off

30 days

(24.12. + 31.12. additionally day off)

Overtime is compensated by additional time off

Benefits

Up to 60% mobile work for suitable tasks, mostly two-person offices, bus and subway (U6) on the doorstep, free parking, pension plan of the Versorgungsanstalt des Bundes und der Länder (VBL), state-of-the-art work equipment, Cooperation Agreement with Sports Facility Providers for Discounted Membership

What you can expect at LRZ:

Are you looking for a multifaceted and intellectually stimulating position in a dynamic, cooperative and innovative work environment? Then LRZ is the place to be for you! Here at LRZ a collegial, appreciative work environment meets an international crowd of experts who work together to advance IT services for ground-breaking research. We offer flexible work schemes for an optimal work-life balance. Our staff values their creative leeway. As an institute of the Bavarian Academy of Science and Humanities we offer all the benefits of public service. And of course, no wishes remain unfulfilled at the LRZ in terms of technical equipment. We share experiences, constantly review and improve our processes, and are proud that our service-quality and data-security are regularly certified and rated highly.We actively promote diversity and welcome applications from talented individuals, regardless of cultural background, nationality, ethnicity, gender and sexual identity, physical abilities, religion and age. We give priority to applications from people with disabilities who are equally qualified (SGB IX).

Are you unsure whether the job suits you or you suit us? Or do you still have questions about this position? Our colleagues will be happy to answer all your questions.

Hereyou will find information about the collection of personal data during the application process.