HPC Scientific Software Engineer (IT@JH Research Computing)

IT@JH Research Computing is hiring an HPC Scientific Software Engineer to support faculty, researchers, and students doing high-performance and AI-driven research across Johns Hopkins University. You would deploy, optimize, and maintain scientific software and computational workflows on advanced HPC systems, working mostly in Linux environments. The job mixes ticket-based user support with longer project work, and you would coordinate with systems engineers and research computing leadership while operating with significant independence.

What you will do

• Develop and refine deployment strategies for scientific software on HPC and AI systems, and design computational workflows using tools like Ansible for automation.
• Help teams implement, tune, and optimize AI models and gateway applications such as XDMoD, Coldfront, Open OnDemand, CryoSPARC Live, SBGrid, and AI Agents.
• Analyze and optimize performance of AI models and HPC applications, with a focus on GPU-enabled computing, parallel processing, distributed computing, and resource management.
• Develop, debug, and maintain software tools, libraries, and frameworks for HPC and AI workloads, using CUDA, DNN, TensorRT, and Intel Compilers.
• Work with the system team and vendors such as NVIDIA, Intel, and Matlab to optimize systems.
• Manage and support scientific software deployment across HPC, cloud-based, and colocation facilities, including installation, configuration, and maintenance with CMake, Make, EasyBuild, Spack, and Lua module files.
• Resolve complex technical issues, perform root cause analysis, and put solutions in place to prevent recurrence.
• Provide training workshops for researchers and students on troubleshooting, optimizing workflows, and using HPC systems.
• Develop and manage container orchestration strategies, overseeing the container lifecycle from creation to removal.
• Write documentation for system designs, performance metrics, and project status, and ensure compliance with security and regulatory standards.
• Mentor junior engineers and work with researchers, data scientists, and software developers on HPC and AI challenges.

What they are looking for

• Master's degree in computer science or a closely related quantitative discipline.
• Five years of experience in HPC user support, software deployment, and performance optimization in an academic or research environment.
• Experience in scientific computing environments and applications.
• Hands-on experience with SLURM for job scheduling.
• Proficiency in Python, Perl, C/C++, and Shell scripting for automation and system management.
• Advanced knowledge of Linux systems.
• Familiarity with scientific application management tools such as containerization, LUA modules, CMake, Spack, and EasyBuild.
• Experience with training workshops, performance optimization, and troubleshooting.

Additional education may substitute for required experience, and additional related experience may substitute for required education beyond a high school diploma or equivalent, to the extent permitted by the JHU equivalency formula.

A PhD in a quantitative discipline such as computer science engineering, physics, or bioinformatics, with advanced training in scientific computing, is preferred.

Pay, hours, and location

The starting salary range is $85,500 to $149,800 per year, commensurate with experience. This is a full-time, exempt position. The schedule is Monday through Friday, 8:30am to 5pm. The location is remote.

The classified title is HPC Scientific Software Engineer, role/level/range ATP/04/PF. The department is IT@JH Research Computing (60014601), personnel area University Administration.