Engineering Manager, CUDA Math Libraries & Platforms

NVIDIA; Pennsylvania; On-site; USD 272,000 - 431,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a Software Engineering Manager to lead a team responsible for platform expansion and readiness, enabling CUDA Math Libraries on new platforms. You will oversee end-to-end platform readiness, integration, and performance validation across CUDA libraries, collaborating with CI/CD, build, and QA teams.

Ideal candidates have strong hands-on C++/Python experience in HPC, 8+ years in numerical software, and 3+ years in leadership. Equity and benefits are offered.

Qualifications

• PhD or MSc degree in Computational Science and Engineering, Computer Science, Applied Mathematics, or related field.
• 8+ years of experience developing high-performance numerical software.
• 3+ years leading and mentoring software engineering teams.
• Hands-on experience with C++ and Python for HPC workloads.
• Strong understanding of numerical methods and computations in science/engineering.
• Excellent communication, collaboration and documentation habits.
• Experience with CI/CD and project-management tools such as JIRA.

Responsibilities

• Lead, mentor, and develop your team.
• Own end-to-end platform readiness across Math Libraries for specialized platforms.
• Collaborate with CI/CD, build, and test infra teams for qualification pipelines.
• Perform defect triage and fix platform/library issues for correctness.
• Identify performance targets and establish testing to fix regressions.
• Define a technical roadmap for platform readiness across multiple platforms.
• Coordinate with library teams, CUDA, compilers, QA, and release groups.

Skills

C++

Python

Parallel computing

HPC software

OOP

Software architecture

Communication

Education

PhD or MSc in Computational Science & Engineering / CS

Tools

CI/CD

JIRA

Large-system software tooling

Job description

NVIDIA is seeking a Software Engineering Manager to lead a team responsible for platform expansion and readiness, enabling CUDA Math Libraries on new platforms. You will oversee end-to-end platform readiness, integration, and performance validation across CUDA libraries, collaborating with CI/CD, build, and QA teams.

Ideal candidates have strong hands-on C++/Python experience in HPC, 8+ years in numerical software, and 3+ years in leadership. Equity and benefits are offered.