Senior Math Libraries Engineer – AI and HPC

at Nvidia

USD 184,000-356,500 per year

SENIOR

✅ On-site

Tech Stack
Tag name is followed by "@" symbol and proficiency level value. About proficiency levels:

1-2 — basic awareness. Minimal hands-on experience, and a rudimentary understanding of the technology's purpose;

3-6 — daily use. Comfortable and regular usage, capable of handling common tasks and challenges related to the technology;

7-9 — you are an expert, you can teach others, you know all the pitfalls and tricks;

10 — exceptional knowledge, comprehensive understanding, and adeptness in all aspects of the technology, including advanced problem-solving. Think twice before claiming or demanding such level.

AI Agile @ 4 CUDA @ 4 Communication @ 7 Deep Learning @ 7 GPU @ 7 HPC @ 4 Jira @ 4 Leadership @ 6 MPI @ 4 Machine Learning @ 7 Mathematics @ 4 NLP Parallel Programming @ 4 Performance Optimization @ 4 Product Management @ 4 Project Management @ 4 Python @ 4 Software Development @ 4 Technical Leadership

Details

NVIDIA's Math Libraries team is looking for a senior engineer to join development efforts in kernel generation for AI and HPC, specifically targeting matrix operations, JIT compilation, and fusions. The team develops GPU-accelerated mathematical libraries used in AI, scientific and engineering simulations, data analytics, healthcare, NLP, VR, deep learning, autonomous vehicles, and other applications.

Responsibilities

Scope, design, and implement high-quality, high-performance numerical dense linear algebra software on GPUs.
Own the execution of projects involving multiple engineers and, at times, multiple teams.
Provide technical leadership and feedback to library engineers and mentor interns when appropriate.
Work closely with product management and internal and external customers to understand feature and performance requirements and contribute to library technical roadmaps.
Identify opportunities to improve library performance and reduce code maintenance overhead through re-architecting.
Develop and explain complex solutions, exercise leadership, and coordinate with multiple teams.

Requirements

PhD, master's, or bachelor's degree in Computer Science, Applied Mathematics, or a related science or engineering field, or equivalent experience.
8 or more years of experience designing, developing, testing, maintaining, and optimizing the performance of HPC software using C++.
Strong fundamentals in kernel generation and composable library design for linear algebra.
Leadership skills in driving software development projects.
Strong collaboration, communication, and documentation habits.
Experience with or a focus on kernel generation and JIT compilation.

Preferred Qualifications

Experience with parallel programming, ideally using CUDA, MPI, OpenMP, OpenACC, or pthreads.
Understanding of machine learning and deep learning technologies, as well as GPU or CPU hardware architecture; GPU knowledge is preferred.
Low-level assembly programming experience for performance optimization and operator fusion.
Experience with agile software development practices and project management tools such as JIRA.
Experience with a scripting language, preferably Python.

Compensation and Benefits

Base salary range of 184,000 USD to 287,500 USD for Level 4.
Base salary range of 224,000 USD to 356,500 USD for Level 5.
Eligibility for equity and benefits.
NVIDIA is committed to fostering a diverse work environment and is an equal opportunity employer.

Applications will be accepted at least until April 12, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes.