HPC Storage Performance Engineer
Role details
Job location
Tech stack
Job description
This role has been designed as 'Hybrid' with an expectation that you will work on average 2 days per week from an HPE office., * Successfully complete long and short-term benchmark projects involving some of the largest HPC systems in the world that utilize the latest HPC technologies.
- Understand HPC architectural components and features, as well as performance estimation methodologies used to provide required information and performance assessments for storage benchmarks on future HPE and competitive systems.
- Provide technical analysis of I/O in standard HPC storage and application benchmarks.
- Identify solutions, define action plans, and help coordinate and deliver optimal benchmark enhancements and solutions in partnership with account teams.
- Develop and maintain current knowledge of competitors' and HPE's HPC products and relevant HPC performance optimization techniques to ensure HPE's ability to provide high-quality benchmark performance results.
Requirements
-
10+ years of related working experience is required.
-
Deep understanding of the HPC Storage environment, including Lustre architecture, tuning, and metrics gained through experience in HPC and AI environments
-
Experience with storage benchmarks, profiling tools and/or scientific/engineering software for HPC systems.
-
Familiarity with analyzing the role of storage in I/O synthetic benchmarks and end-user application performance.
Preferred Qualifications:
-
Experience in one or more of the following storage solutions: DAOS, GPFS, WekaIO, VAST, BeeGFS.
-
Knowledge of HPC system components interaction with HPC benchmarks in addition to storage including processor, accelerator, memory, and software technologies
-
Understanding of parallel programming techniques and algorithms.
-
Ability to triage complex issues, provide test cases and interact with R&D groups as part of a process to report and fix bugs.
-
Expertise with software utilized by the HPC community that includes Compilers (C++, C, Fortran), OpenMP, MPI, MPI-IO, Python and other Linux based scripting languages
-
Expertise in GPU programming (CUDA and HIP)
-
BS (Masters Preferred) degree in in a Science, Technology, Engineering or Mathematical discipline.