Job Details

Home Office (New York)
Full time
R0001206


POSITION SUMMARY

The Scientific Computing Core (SCC), co-led by Nick Carriero and Ian Fisk, manages

supercomputing resources and provides high performance computing (HPC) expertise to

all centers at the Flatiron Institute, a division of the Simons Foundation, developing tools

broadly useful to the scientific community as a whole.

As new GPUs become available from different vendors comes the question for programmers developing scientific software to choose the tools to port their applications to the new architectures. Several standardization attempts have been made before, but none came to fruition. However, with the most recent supercomputers installed all using a novel architecture, this has greatly renewed interest in this field.

SCC is seeking a Scientific Computing Intern to apply their software engineering skills to assess the programmability of the different available tools, as well as benchmark the resulting programs on a practical problem. The focus will be on dense linear algebra. The selected candidate will have a chance to test and use modern GPU equipment, along with advanced programming models. They will be on SCC premises daily to meet with their advisor, collaborate with scientists from a broad range of disciplines, present their progress, and participate in discussions. At the completion of their projects, they will present their work orally and potentially prepare a research paper.

This is a paid, full-time internship that will run from May 30 through August 11, and will take place in our New York City offices. Travel to New York City, and housing may be available for interns based outside of the five boroughs of New York City.

ESSENTIAL FUNCTIONS/RESPONSIBILITIES

• Assist in evaluating the different tools and languages available to program modern GPUs


• Apply that knowledge to a practical application: dense matrix factorizations


• Use github to effectively collaborate on team programming projects


• Use Flatiron cluster resources to profile/benchmark/test software

MINIMUM QUALIFICATIONS

Education

• Must be a student enrolled in an accredited undergraduate or graduate degree program


• Students enrolled in physics, mathematics, computer science, or related disciplines preferred


• Strong oral and written communication


• Excellent collaborative and interpersonal skills

Required Experience

• Experience with Unix (Linux)


• Written or made a major contribution to a significant project in one of the following languages: C/C++, Fortran, CUDA

Desirable Experience

• Understanding of (though not necessarily practical experience in) HPC and cluster computing topics such as MPI, OpenMP, GPU


• Course in linear algebra and basic knowledge of matrices (this work will require using/programming matrix multiplications)


• GPU Programming


• Basic knowledge of git

Related Skills & Other Requirements

• Must enjoy working in a vigorous research-driven environment


• Desire to document code and process, deliberative decision-making.

Required Application Materials

• Resume or CV


• Cover letter indicating your interest in the position


• If available, please include GitHub or other code links

Deadlines

• Applications for summer 2023 must be submitted by February 1, 2023

COMPENSATION

• This internship pays $20 to $25 per hour, depending on experience.

THE SIMONS FOUNDATION'S DIVERSITY COMMITMENT

Many of the greatest ideas and discoveries come from a diverse mix of minds, backgrounds and experiences, and we are committed to cultivating an inclusive work environment.The Simons Foundation actively seeks a diverse applicant pool and encourages candidates of all backgrounds to apply.We provide equal opportunities to all employees and applicants for employment without regard to race, religion, color, age, sex, national origin, sexual orientation, gender identity, genetic disposition, neurodiversity, disability, veteran status, or any other protected category under federal, state and local law.