Nvidia Senior Math Libraries Engineer – AI HPC 

United States, Texas 

415814191

What you will be doing:

• Scoping, designing, and implementing high quality and performance numerical dense linear algebra software on GPUs.

• Owning the execution of projects involving multiple engineers and sometimes teams.

• Providing technical leadership and feedback to library engineers working with you on projects and sometimes mentor interns.

• Working closely with product management and other internal and external customers to understand feature and performance requirements and contribute to the technical roadmaps of libraries.

• Finding opportunities to improve library performance and reduce code maintenance overhead through re-architecting.

• To be successful in your responsibilities which are by nature sophisticated, you will need to find and explain complex solutions, exercise leadership, and coordinate with multiple teams to work towards your goals.

What we need to see:

• PhD or Master’s degree in Computer Science, Applied Math, or related science or engineering field of study (or equivalent experience).

• 5+ years of experience in designing, developing, testing, maintenance, and performance optimization 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.

• Kernel generation. JIT focus/experience desired

Ways to stand out from the crowd:

• Experience with parallel programming, ideally using CUDA, MPI, OpenMP, OpenACC, pthreads.

• Good understanding of Machine Learning and Deep Learning technologies.

• Good knowledge of GPU (preferred) or CPU hardware architecture.

• Experience with low level programming using assembly for performance optimization and operator fusion is a huge plus.

• Experience with agile software development practices using project management tools such as JIRA.

• A scripting language, preferably Python.