Platform Readiness Lead for CUDA Math Libraries

NVIDIA; Washington (District of Columbia); On-site; USD 224,000 - 431,000; Full time

Benefits offered by this job

Equity

Benefits

Annual bonus

Job summary

NVIDIA seeks an Software Engineering Manager to lead a team focused on expanding and readying CUDA Math Libraries across platforms. You will own platform integration, qualification, and performance readiness, collaborating with core library, devops, and QA teams to ensure high-quality support on new architectures.

The role requires hands-on engineering plus leadership experience in accelerated computing, with strong C++/Python, HPC concepts, and a bias for delivering scalable software in a

Qualifications

• PhD or MSc in Computational Science and Engineering or equivalent experience.
• 8+ years of experience developing high-performance numerical software.
• 3+ years leading and mentoring software engineering teams.
• Hands-on in C++ and Python, large system software architecture, HPC performance.
• Strong numerical methods knowledge for science and engineering.
• Experience with CI/CD and project management tools such as JIRA.

Responsibilities

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

Skills

C++

Python

HPC software

Parallel computing

CI/CD

JIRA

Team leadership

Mentoring

Software architecture

Education

PhD or MSc in Computational Science and Engineering

Tools

JIRA

Job description

NVIDIA seeks an Software Engineering Manager to lead a team focused on expanding and readying CUDA Math Libraries across platforms. You will own platform integration, qualification, and performance readiness, collaborating with core library, devops, and QA teams to ensure high-quality support on new architectures.

The role requires hands-on engineering plus leadership experience in accelerated computing, with strong C++/Python, HPC concepts, and a bias for delivering scalable software in a