Senior Math Libraries Engineer - Direct Sparse Solvers

Nvidia

Remote

Quick summary

Work type: Remote
Location: Santa Clara, CA
Salary: $184,000–$287,500 / yr
Posted: 8 days ago
Nearby: 99+ roles within 25 mi

Market check

Salary context

Above market

How this pay compares to similar roles

Similar $216k

This role $236k

$147k most similar roles pay here $303k

This role pays more than 73% of similar roles. Most pay $195,000–$236,900 — the shaded band above. At the midpoint, this role pays about $236k versus about $216k for comparable roles.

Based on 239 similar postings.

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 992 open roles on FindRole.

Listed pay typically runs $168,000–$264,500 across 979 roles with salary data.

Most-posted roles

View all roles at Nvidia

At a glance

TL;DR · Senior Math Libraries Engineer - Direct Sparse Solvers

Apply Now Log in to save

Join our cuDSS team as a senior software engineer where you will design, implement, and optimize direct sparse solvers for GPUs, collaborating closely with library engineers, QA teams, and product management to ensure high-quality releases. Ideal candidates have 5+ years of experience in developing and optimizing numerical software using C++ and CUDA, along with strong fundamentals in floating-point arithmetic and sparse linear algebra. You will work on reordering techniques, multi-frontal factorizations, and GPU performance optimization while adopting modern software engineering practices like CI/CD systems and agile project management tools. This role involves advancing the state-of-the-art in accelerated computing for applications ranging from CAE to AI, contributing to the technical roadmaps of high-performance linear algebra libraries used globally by leading organizations.

Skills

CUDA C++ MPI OpenMP OpenACC pthread CI/CD JIRA Python Git GitHub Linux NVIDIA_GPU Sparse_Linear_Algebra Direct_Solvers Reordering Multi_Frontal_Factorizations Supernodal_Factorizations Numerical_Pivoting_Strategies Iterative_Refinement

What you'll do

Design and implement direct sparse solvers optimized for current and future GPU architectures.
Collaborate with engineers to develop, test, and release high-quality linear algebra libraries.
Engage with product management to define technical roadmaps and feature requirements for libraries.
Identify and execute opportunities to enhance library performance, quality, and maintainability.
Apply advanced techniques in direct solvers like reordering and multi-frontal factorizations.

What we're looking for

PhD or MSc in Computer Science, Computational Science, Applied Mathematics, or related field (or equivalent experience)
5+ years developing high-performance numerical software with C++ and parallel programming technologies like CUDA
Strong expertise in floating-point arithmetic, numerical analysis, and sparse linear algebra primitives
Experience in developing, maintaining, and testing scientific computing libraries
Familiarity with direct solvers techniques including reordering and multi-frontal factorizations
Knowledge of CPU/GPU hardware architecture and low-level GPU performance optimization
Experience with modern software engineering methods like CI/CD systems and project management tools

Similar roles

Senior ML Infrastructure Engineer - VE Algorithms

Apple Inc

San Diego, CA 56 days ago $139,500–$258,100

Python PyTorch C++ Docker Kubernetes AWS CI/CD Prometheus Grafana PostgreSQL

Save

Large Machine Learning Model Optimization Engineer, SIML

Apple Inc

Seattle, WA 39 days ago $139,500–$258,100

Python model compression quantization pruning distillation diffusion models language models hardware-aware model optimizations ML compiler high performance kernel implementation distributed inference

Save

Large Machine Learning Model Optimization Engineer, SIML

Apple Inc

Seattle, WA 93 days ago $139,500–$258,100

Python model compression quantization pruning distillation diffusion models language models hardware-aware model optimizations ML compiler high performance kernel implementation distributed inference

Save