Engineering Manager, Math Libraries Platform Expansion and Readiness

Details

We are looking for a Software Engineering Manager to lead a team responsible for platform expansion and readiness, enabling CUDA Math Libraries on new and specialized platforms. NVIDIA's math libraries are core to AI infrastructure and must deliver functionality and performance on every target.

In this role, you will lead and build a team that provides a single accountable organization for platform integration, functional qualification, compliance, and performance readiness across CUDA Math Libraries. You will work closely with core library and DevOps engineering teams to ensure consistent, high-quality support on every expanding platform.

Responsibilities

• Lead, mentor, and develop the team.
• Own end-to-end platform readiness across Math Libraries for specialized platforms, including integration, functional qualification, and compliance.
• Collaborate with CI/CD, build, and test infrastructure teams to establish platform-specific qualification and validation pipelines.
• Perform defect triage and isolate platform-specific problems from library-specific problems.
• Fix bugs to ensure functional correctness and refer issues to library specialists as needed.
• Identify performance targets for new platforms, establish performance testing, and fix performance regressions.
• Define and deliver a technical roadmap for platform readiness that scales with the number and complexity of supported platforms.
• Coordinate dependencies across library teams, CUDA, compilers, QA, release processing, and platform organizations in collaboration with product, engineering, and program managers.

Requirements

• PhD or MSc degree in Computational Science and Engineering, Computer Science, Applied Mathematics, or a related science or engineering field, or equivalent experience.
• 8+ years of overall experience developing high-performance numerical software.
• 3+ years of experience leading and mentoring software engineering teams.
• Hands-on experience with object-oriented programming, large-system software architecture development, parallel computing, testing, maintenance, and performance optimization of HPC software using C++ and Python.
• Strong understanding of fundamental numerical methods and computations in science, engineering, and/or deep learning.
• Strong communication, collaboration, and documentation habits.
• Experience with, and motivation to adopt and advance, software development practices such as CI/CD systems and project management tools such as JIRA.

Preferred Qualifications

• Experience with CUDA, GPU-accelerated computing, and parallel programming, including MPI, OpenMP, OpenACC, or pthreads.
• Familiarity with math libraries such as BLAS, LAPACK, FFT, and sparse solvers.
• Proven track record using Agentic AI to improve efficiency and code quality.
• Experience with cross-platform software development and platform bring-up across multiple architectures.
• Experience delivering software for safety-critical or embedded environments, such as DriveOS and ISO 26262.

Compensation and Benefits

The base salary range is USD 224,000–356,500 for Level 3 and USD 272,000–431,250 for Level 4. Compensation is determined based on location, experience, and the pay of employees in similar positions. The role is also eligible for equity and benefits.

Applications will be accepted at least until October 2, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes. NVIDIA is committed to fostering an inclusive work environment and is an equal opportunity employer.