Senior Systems Software Engineer, Compute Stack Acceleration
Core
Lead cross-stack engineering efforts to adopt modern toolchains, build practices, and performance workflows across NVIDIA CPU platforms, turning ambiguous adoption problems into measurable outcomes.
Role type
Senior Systems Software Engineer (Compute Stack Acceleration)
Builds
Repeatable engineering practices, automation wrappers, validation scripts, and dashboards for toolchain and performance improvements.
Domain
High-Performance Computing (HPC), CPU architecture, Compiler toolchains
Required skills
C/C++ development, Linux systems, GCC/LLVM/Clang toolchains, build systems, performance profiling, root-cause analysis, project leadership
Preferred skills
Arm64 systems, CPU architecture, vectorization, LTO/PGO/AutoFDO/BOLT, Clang diagnostics, PMU analysis, cross-compilation, Python scripting
Technologies
GCC, LLVM/Clang, Linkers, AutoFDO, BOLT, perf, flamegraphs, Python
Responsibilities
Lead toolchain and build system adoption projects; Evaluate and deploy compiler options and cross-compilation configurations; Integrate workflows into CI environments; Establish Clang diagnostic builds and sanitizer coverage; Use profiling data to identify performance findings; Build automation and validation scripts; Drive blockers to appropriate owners; Document reusable playbooks.
Seniority
Senior, hands-on IC
