High Performance Compute (HPC) Software Engineer – HPC SW Systems
KLA-TencorAnn Arbor, MI · full time
$105,900 – $180,000
Listed on KLA-Tencor’s own careers site. You apply with them directly — we never stand between you and the employer.
What this role is
This role designs and optimizes high-performance computing software for large-scale Linux clusters used in semiconductor manufacturing, requiring deep expertise in parallel computing, system-level performance tuning, and hardware-software co-design. It suits engineers with strong foundations in systems programming who want to work on mission-critical infrastructure that directly impacts production tools at scale.
Our summary, not KLA-Tencor’s wording. The full posting is on their site.
Skills this role names
Log in to see which of these are already on your profile.
What they ask for
Required
- Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent practical experience
- Strong HPC or systems software development experience on Linux
- Proficiency in Java and/or C++ and/or other system-level or performance-oriented languages
- Hands-on experience with parallel computing such as MPI, OpenMP, or multithreading
- Solid understanding of HPC hardware fundamentals: CPUs, memory hierarchies, storage, and networking
- Practical experience working with clusters, servers, or rack-scale systems in lab or production environments
- Strong debugging skills across software, OS, and hardware boundaries
Nice to have
- Experience with containerized HPC environments including Docker, Singularity/Apptainer, or Kubernetes in HPC contexts
- Familiarity with high-speed interconnects, storage architectures, and performance benchmarking
- Exposure to rack integration including cabling, power distribution, cooling, and system bring-up
- Experience in semiconductor, manufacturing, or high-reliability systems environments
- Ability to reason about system reliability, MTBF/MTBA, and failure modes in large compute installations
- GPU computing experience with CUDA, ROCm, or equivalent