Sparse Linear Algebra Libraries Intern

What you'll do

• Prototype and develop numerical algorithms for high-performance sparse linear algebra libraries on GPUs.
• Analyze the performance of GPU implementations to identify and implement optimization opportunities.
• Implement new numerical algorithms for sparse matrix-vector and sparse matrix-matrix products.
• Define APIs for high-performance computing and deep learning software stacks.
• Identify and resolve solutions for difficult numerical corner cases.
• Utilize code/kernel generation techniques to optimize operations for unstructured sparse matrix inputs.
• Perform general software engineering tasks including debugging, performance analysis, and test design.

What we're looking for

• Pursuing an MS or PhD in Computational Science, Computer Science, Applied Mathematics, or an equivalent program area.
• Strong C++ programming, debugging, performance analysis, and test design skills.
• Experience implementing sparse linear algebra algorithms.
• Parallel programming experience using CUDA and/or OpenMP.
• Experience with domain-specific language design, code/kernel generation, and compiler optimizations.
• Exposure to numerical methods, floating-point arithmetic, and numerical error analysis (preferred).
• Knowledge of GPU/CPU and network hardware architecture (preferred).
• Proficiency in a scripting language, preferably Python (preferred).