Senior System Software Engineer - Slurm
Core
Design, maintain, and optimize the Slurm workload manager (written in C) for HPC environments, including system-level components, networking, and device integration.
Role type
Senior System Software Engineer (HPC)
Builds
Slurm Workload Manager for High Performance Computing clusters
Domain
High Performance Computing (HPC), Linux Systems, GPU Computing
Required skills
C programming, Linux kernel interfaces, system calls, memory management, pointers, data structures, algorithms, debugging tools (GDB), performance profiling, build systems (Automake), containers, GPU technologies
Preferred skills
Slurm Workload Manager experience, High Performance Computing background, operating system internals, hardware-software interaction, open-source C contributions
Technologies
C, Linux, GDB, Automake, Containers, GPU
Responsibilities
Maintain and optimize software components in C; Develop system-level and application-level code for Slurm including networking and device components; Debug and fix complex Slurm issues related to reliability and performance; Write clean, maintainable, and well-documented code; Collaborate with Operations, Infrastructure, and Deployment teams; Provide direct technical support to internal teams or external customers; Develop automated tests to ensure software reliability and regression prevention
