HPC Systems Administration Specialist

Argonne National Laboratory; Lemont (IL); On-site; USD 75,000 - 135,000; Full time

Job summary

Argonne National Laboratory seeks an HPC software integration specialist to design, develop, and advance the HPC environment within the ALCF. You will focus on software integration with the broader ecosystem, maintaining Spack environments, and building complex scientific software for exascale architectures.

You will work with application owners and domain scientists to profile, debug, and optimize performance, report issues upstream, and document build procedures and optimization strategies to

Qualifications

• Experience with Spack, CMake, Make, and managing software dependencies in Linux-based HPC environments.
• Proficiency in compiling large-scale scientific applications from source using various compilers and MPI libraries.
• Familiarity with profiling and tuning tools to optimize applications beyond default installations.
• Excellent interpersonal skills and ability to work with scientists, researchers, and external developers.

Responsibilities

• Assist with the design, development, and advancement of the HPC environment of the ALCF and focus on software integration with the larger software and operational ecosystem at the facility site.
• Package & Environment Management: Maintain, configure, and optimize Spack environments across ALCF systems to support a diverse portfolio of scientific applications.
• Compilation & Integration: Build, compile, and validate complex scientific software across heterogeneous exascale architectures.
• Performance Tuning & Collaboration: Profile, debug, and tune codes for maximum hardware efficiency in collaboration with application-owners.

Skills

HPC build & packaging

Collaboration & communication

Performance tuning

Documentation & support

Education

Bachelor's degree

Master's degree

Tools

Spack

CMake

GNU Make

MPI libraries

Job description

Argonne is a multidisciplinary science and engineering research facility, where world-class researchers work alongside experts from industry, academia, and other government laboratories to address vital national challenges in technology and national security. As a member of the Argonne Leadership Computing Facility (ALCF) High Performance Computing (HPC) team, you will directly work with first-class supercomputers and emergent technologies alongside scientific staff and research colleagues within the division. In this role, you will be able to significantly contribute to the design and development of new HPC systems, tools, and software stacks.

In this role you can expect to:

• Assist with the design, development, and advancement of the HPC environment of the ALCF and focus on software integration with the larger software and operational ecosystem at the facility site.
• Package & Environment Management: Maintain, configure, and optimize Spack environments across ALCF systems to support a diverse and evolving portfolio of scientific applications.
• Compilation & Integration: Build, compile, and validate complex scientific software using modern build systems (e.g., CMake, GNU Make) tailored to heterogeneous exascale architectures (CPUs, GPUs, and accelerators).
• Performance Tuning & Collaboration: Work hand-in-hand with application-owners and domain experts after initial compilation to profile, debug, and performance-tune codes for maximum hardware efficiency.
• Upstream Engagement & Issue Reporting: Identify software defects or build failures, and effectively report and track issues back to external software developers and open-source communities.
• Documentation & Support: Document installation procedures, custom build flags, and optimization strategies, providing expert-level support to open-science researchers relying on your software stack.

Position Requirements

• HPC Build & Package Tools: Demonstrated experience with Spack, CMake, Make, and managing software dependencies in Linux-based high-performance computing environments.
• Compilation & Debugging: Strong proficiency in compiling large-scale scientific applications from source, utilizing various compilers (GNU, LLVM/Clang, Intel, etc.) and MPI libraries.
• Performance Tuning: Familiarity with profiling and tuning tools to optimize applications beyond default installations.
• Collaboration & Communication: Excellent interpersonal skills with a proven track record of working closely with domain scientists, researchers, and external developers to troubleshoot and refine software.
• Core Values: Ability to model Argonne's core values of impact, safety, respect, integrity and teamwork.
• US Citizenship: To perform the essential functions of this position successful applicants must provide proof of U.S. citizenship, which is required to comply with federal regulations and contract.

This position can be hired at one of two levels; the selected candidate will be placed at the appropriate level (PT2 or PT3) dependent upon the depth and breadth of relevant knowledge and skills. The minimum requirements for the two levels are as follows:

• PT2: Minimum of a Bachelors degree and 2+ years of experience, or equivalent and the expected hiring range for this level is $69,750 - $108,810.
• PT3: Minimum of a Bachelors degree and 4+ years of experience, or a Masters degree and 2+ years, or equivalent and the expected hiring range for this level is $86,299 - $134,626.