Senior Software Engineer, CUDA Core Libraries
NVIDIA Corporation · Santa Clara, CA
$184,000–$356,500from the description
Jul 13, 2026
Santa Clara, CA
Jul 21, 2026
What this job asks for AI summary
A senior engineering role focused on building and maintaining Python APIs, language bindings, and runtime infrastructure for CUDA's core GPU-accelerated libraries, with substantial work also done in C/C++. The position spans the full feature lifecycle — from API design and native integration to testing, packaging, and documentation — and involves defining interoperability boundaries across Python, C/C++, and Rust. Suited to engineers with deep experience in both Python and systems-level programming, ideally with a GPU or parallel computing background.
Senior level · 8+ years · Remote · Full-time
“or” means any one of them counts — you don't need all of them.
We read this from the posting text with AI. Skim the description below before ruling yourself out.
How this req sits in the market our data
Roughly 28,200 people nationally plausibly meet what this posting asks for (software developers). range 11,800–42,300
Applicant volume Moderate — A normal amount of company. The rare requirements below are what will separate a shortlisted application from the rest.
Most people in this occupation already list these. Still required — just not what gets you shortlisted.
What the occupation pays Median $138,970 (middle half $107,524–$175,762). This posting is about at that midpoint.
Estimated from BLS employment for this occupation and area, per-skill prevalence across our listing corpus, and published wage benchmarks — as of Jul 28, 2026. It is a model, not a headcount.
Why we read it this way (8)
The posting advertises two salary bands — $184,000–$287,500 (Level 4) and $224,000–$356,500 (Level 5) — reflecting that the hire could land at either level. The min and max reported here span the full combined range.
A BS/MS/PhD in CS or related field is listed, but the JD explicitly accepts 'equivalent experience,' so no formal degree is treated as a hard gate.
GPU programming experience (parallel, heterogeneous, or GPU) is listed under the required qualifications section; specific GPU stacks (CUDA C++/Python, PyTorch, JAX, Numba, CuPy) appear only under 'Ways to stand out from the crowd' and are marked preferred.
Thrust, CUB, and libcudacxx are grouped together under 'Ways to stand out' and are marked preferred; one skill is emitted with the others as alternatives since they are closely related GPU library peers.
LLVM, Clang, and MLIR appear together under 'Ways to stand out' as compiler infrastructure experience; marked preferred with alternatives.
Rust is called out under 'Ways to stand out' as exposure in mixed-language stacks; marked preferred.
Remote status is set per caller instruction; no metro is inferred.
Caller marked this a fully-remote role — scored against the national candidate pool.
Read the full posting
The employer publishes the full description on their own site — read it there ↗. Or sign in to read it here — it's free, and it also lets you track this application.