- The HPC Software Engineer (HSE) designs, develops; tests, deploys, documents, maintains, and enhances complex and diverse software for HPC (high performance computing) systems based upon documented requirements, Critical for an HSE is either a very strong math background and/or a very strong Computer hardware background, One or both of these is required in order for the HSE to be able to understand the intricacies of the HPC architecture that is being targeted by the software being developed, or to understand the complex mathematical principles which-underlie the software applications being developed. The systems might include, but are not limited to, processing-intensive analytics, novel algorithm development, manipulation of extremely large data sets, real-time systems, and systems which incorporate data repositories, data transport services, and application and systems development and monitoring. Works -individually or as part of a team.
- The contractor shall be tasked with designing, developing, testing, deploying, and documenting complex and diverse software solutions in a Unix High Performance Computing (HPC) environment.
- Additional tasking shall include design and development of new software as well as integration and modification of existing software to system components. Contractor shall be responsible for performing characterization and performance tuning of various software stacks throughout the system including managing the software and system test development, performance, and benchmarking for each HPC node type throughout the System of Systems.
- Analyze user requirements to derive software design and performance requirements.
- Debug existing software and correct defects.
- Design and code new software or modify existing software to add new features.
- Write or review software and system documentation.
- Integrate existing software into new or modified systems or operating environments.
- Develop simple data queries for existing or proposed databases or data repositories
- Has experience with agile development processes.
- Has experience with source code control systems, such as Git.
- Experience using collaboration and software development tools (i.e., Atlassian). Develop and execute test procedures for software components.
- Software development using continuous integration practices.
- Develop software solutions by analyzing system performance standards and conferring with users or system engineers; analyzing systems flow, data usage and work processes; and investigating problem areas.
- Unix shell scripting.
- Experience developing software for HPC systems using parallel development languages/paradigms such as SHMEM, MPI, UPC, Chapel, or P-Threads.
- Experience developing software targeted to take advantage of a specific architecture’s unique features, whether those features are in the processor, memory, network, storage, or other area of an HPC system.
- Modify existing software to adapt to new hardware or to improve its performance.
- Design, develop, and modify software systems, using scientific analysis and mathematical models to predict and measure outcomes and consequences of design decisions.
- Development of assemblers, compilers, simulators, drivers, board support packages, health & status monitoring packages, and other low-level software.
- Development of event driven or data driven analytics.
- Develop or implement algorithms to meet or exceed system performance and functional standards.
- Develop or modify software to optimally map algorithms to a particular hardware architecture.
- Experience with container technologies, such as Docker.
- Recommend and implement suggestions for improving documentation and software development process standards.
- Oversee one or more software development teams and ensure the work is completed in accordance with the constraints of the software development process being used on any particular project.
- Confer with system engineers and hardware engineers to derive software requirements and to obtain information on project limitations and capabilities, performance requirements, and interfaces.
- Coordinate software installation on a system and monitor performance to ensure operational specifications are met.
- Demonstrated experience improving software performance through analysis and optimization of software algorithms or by devising a novel software approach to take advantage of new or unique hardware features.
- Recommend new technologies, techniques, and processes for complex software projects.
- Serve as the technical lead of multiple software development teams.
- Ensure quality control of all developed and modified software.
- Delegate programming and testing responsibilities to one or more teams and monitor their performance.
Technical Skills Required:
- Experience developing scripts using Bash/Python
- Experience using the Unix command line
- General HPC technical knowledge regarding compute, network, memory, and storage components
- Experience developing with multiple high level programming languages in a Unix environment
- Experience with HPC open source parallel programming methods such as OpenSHMEM, pthreads, Open MPI, and UPC
- Experience developing test plans, operational assessment test reports, and associated documentation
- Experience with containerization technologies such as Docker
- Experience with automating test procedures
- Experience with performing benchmarking testing
Special Technical Skills Desired:
- Experience with Git source code repository
- Experience with the Atlassian Suite of Tools (Jira, Confluence)
Minimum Experience Required:
- Master’s degree in Math, Computer Engineering, Computer Science, or related discipline from an accredited college or university, plus five (5) years of experience as an HSE, in programs and contracts of similar scope, type, and complexity. OR Bachelor’s degree in Math, Computer Engineering, Computer Science, or related discipline from an accredited college or university, plus seven (7) years of experience as an HSE, in programs and contracts of similar scope, type, and complexity. OR Nine (9) years of experience as an HSE, in programs and contracts of similar scope, type, and complexity
- TS/SCI with Polygraph Required