The University of Tennessee, Knoxville’s Innovative Computing Laboratory (ICL) is seeking full-time Post Doctoral researchers in several areas of high-performance computing (HPC), including: (1) Distributed Computing; (2) Performance Measurement and Modeling; and (3) Numerical Linear Algebra. ICL is directed by Jack Dongarra, Distinguished Professor of Electrical Engineering and Computer Science at the University of Tennessee, Knoxville.
Prospective researchers will work in a team-based, deadline-driven environment with the opportunity to: (1) participate in the design, development, and maintenance of software libraries and programming environments for large, distributed-memory hybrid machines; (2) extend and harden the performance monitoring capabilities of ICL’s software for new and advanced hardware and software technologies; or (3) develop and maintain numerical software libraries for solving linear algebra problems on hybrid machines with multi-core processors and hardware accelerators.
The prospective researcher will co-author papers to document research findings, present the team’s work at conferences and workshops, and help lead students and other team members in the lab’s multiple research and development efforts, which are supported by the U.S. Department of Energy’s Exascale Computing Project and the National Science Foundation.
Required Education:
- PhD in Computer Science, a computational science, or related field with demonstrable background in: applied mathematics; HPC; computer architectures and parallel processing; or distributed, multi-core, and GPU computing.
Required Experience:
A successful candidate will have a background in one or more of the following areas:
- Distributed Computing – some background in HPC, resilience, programming models, and network and parallel algorithms.
- Performance Measurement and Modeling – technical experience in system software, parallel computing, scientific applications, and low-level libraries; prior experience and expertise with systems programming, benchmarking, performance analysis toolkits, C, C++, and Fortran are also desired; significant experience developing large software systems is a plus.
- Numerical Linear Algebra – background in applied mathematics; technical experience in parallel computing, distributed computing, and multithreading; familiarity with numerical software libraries; and experience with GPU computing and mathematical software.
Required Job Skills:
The ideal candidate will have extensive knowledge of programming techniques; strong low-level system programming abilities; high proficiency in C/C++; a basic understanding of Fortran; familiarity with numerical software, modern MPI, OpenMP, and CUDA; excellent communication skills; and a strong publication record.
How to Apply
For consideration, submit CV and contact information for three references.