Senior GPU Math Libraries Engineer JIT Kernel Fusion

NVIDIA Corporation; Santa Clara (CA); Hybrid; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Hybrid work model

Job summary

NVIDIA Corporation is seeking a senior engineer to advance kernel generation for AI and HPC, focusing on matrix operations, JITing and operator fusions. You will lead GPU-accelerated linear algebra libraries and coordinate cross-team efforts with PMs and external partners.

The role demands 8+ years in HPC software with strong C++ skills, leadership, and a passion for performance. Hybrid work in Santa Clara, with equity and benefits offered.

Qualifications

• PhD, Master’s, or Bachelor’s degree in Computer Science, Applied Math, or related field (or equivalent experience).
• 8+ years of experience in HPC software design, development, testing, maintenance and performance optimization using C++.
• Strong fundamentals in kernel generation and composable library design for linear algebra.
• Leadership skills in driving software development projects.
• Collaboration, communication, and documentation abilities; JIT focus/experience desired.

Responsibilities

• Scoping, designing, and implementing high quality numerical dense linear algebra software on GPUs.
• Owning the execution of projects involving multiple engineers and teams.
• Providing technical leadership and mentoring engineers and interns.
• Working with product management and customers to shape feature requirements and roadmaps.
• Identifying opportunities to improve performance and reduce maintenance through re-architecting.
• Explaining complex solutions, exercising leadership, and coordinating across teams to achieve goals.

Skills

Leadership

Collaboration

C++ proficiency

Kernel generation

Education

PhD, Master’s, or Bachelor’s degree in CS/Applied Math or related field

Tools

CUDA

MPI

OpenMP

OpenACC

pthreads

Job description

NVIDIA Corporation is seeking a senior engineer to advance kernel generation for AI and HPC, focusing on matrix operations, JITing and operator fusions. You will lead GPU-accelerated linear algebra libraries and coordinate cross-team efforts with PMs and external partners.

The role demands 8+ years in HPC software with strong C++ skills, leadership, and a passion for performance. Hybrid work in Santa Clara, with equity and benefits offered.