Nvidia Senior Library Acceleration Engineer RAPIDS 

United States, Texas 

466489192

We’re growing the team developing core libraries within RAPIDS. In this role, you will develop, benchmark, and architect backend libraries and frontend APIs. This is a great chance to take advantage of your fundamental computer science as well as more practical topics such as the PyData Stack, CUDA, C++, and Python programming skills. You’ll work closely with the RAPIDS team of stellar engineers building highly-optimized CUDA libraries.

What you'll be doing:

• Analyze, design, and implement optimized GPU algorithms for data analytics and machine learning

• Expand and improve integration of RAPIDS into relevant high-level frameworks

• Drive performance analysis, benchmarking, and trouble-shooting of associated libraries.

• Collaborate with a multi-functional team to understand requirements and implement or improve solutions

What we need to see:

• MS or PhD in Computer Science, Computer Engineering or Electrical Engineering or related field in Deep Learning, Machine Learning, and Computer Vision or equivalent experience.

• 5+ years of proven experience in Computer Science, Artificial Intelligence, Applied Math, or related field

• Expert level knowledge in building and maintaining Python interfaces to lower level libraries, preferably in C++ (CUDA a bonus)

• Strong analytical problem-solving skills, algorithms and mathematics fundamentals.

• Excellent software development skills: programming, debugging, performance analysis, and test design

• Good communication and documentation habits.

• Ability to work independently and manage your own development efforts.

• A passion for thoughtful benchmarking

Ways to stand out from the crowd:

• Experience developing distributed algorithms and running on distributed systems: HPC, Cloud, etc

• Background with debugging multi-language and multi-hardware systems

• Experience with PyData: NumPy, Pandas, Scikit-Learn, Dask, Xarray, Zarr

• Prior work on open-source projects

• GPU programming knowledge is a plus, but if you don’t have it, we’re happy to teach you