Join our team as a Senior Software Engineer to design and develop C++-based libraries and tools that simplify and accelerate unstructured sparsity computations in deep learning and high-performance computing on NVIDIA GPUs. You will enable these systems in popular DL frameworks like Python and PyTorch, evaluate their performance, and enhance library quality through effective coding practices. Collaborate closely with product management and external partners to understand requirements and contribute to technical roadmaps. Ideal candidates have a strong background in developing high-performance software using C++, CUDA, MPI, or OpenMP, experience with sparse linear algebra applications, and knowledge of domain-specific language design and compiler optimizations such as MLIR or TACO. This role requires expertise in sparse computations, deep learning methods, GPU performance optimization, and numerical linear algebra techniques like direct and iterative solvers.
Skills
C++
CUDA
Python
PyTorch
MLIR
TACO
MPI
OpenMP
CI/CD
JIRA
GPU
Sparse_Computations
LLMs
Deep_Learning
Numerical_Linear_Algebra
HPC
What you'll do
Design and develop a C++-based system to simplify unstructured sparsity computations on NVIDIA GPUs.
Enable sparse tensor computation systems in Python and PyTorch for broader usage.
Evaluate and enhance performance of developed libraries on real-world applications.
Write high-quality, well-tested code to improve library quality, maintainability, and performance.
Collaborate with product management to understand feature requirements and contribute to technical roadmaps.
What we're looking for
BS, MS or PhD degree in Computer Science, Applied Math, or related field with 6+ years experience in high-performance software development using C++ and parallel programming technologies like CUDA.
Expertise in sparse linear algebra applications, domain-specific language design, and compiler optimizations such as MLIR or TACO.
Proficient in C++, Python, and CUDA programming; strong understanding of sparse computations in AI and HPC.
Experience with low-level GPU performance optimization and numerical linear algebra methods including direct and iterative solvers.
Strong collaboration skills and experience working effectively in a globally distributed team.
Market check
Salary context
This
$184,000–$287,500
range sits above
75%
of similar postings on FindRole.
Peer median band
$161,700–$241,500
Median floor and ceiling across peers.
Typical midpoint (25–75%)
$167,340–$238,162
Middle half of comparable postings.
Based on 240 comparable postings.*
* 240 is the maximum number of comparable postings sampled.
Employer
About Nvidia
Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing
Nvidia currently has
802 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 798 roles with salary data.