An SME – HPC Applications sits between application/users and the HPC infrastructure. The role is more specialized than a general technology associate; you’re expected to understand not just how HPC systems work, but also how applications (scientific, simulation, AI/ML) are built, optimSized, deployed, and scaled on them. You may be involved in performance tuning, user consultation, choosing or improving software / libraries, often working with developers, scientists, or engineers.

Primary Roles & Responsibilities

- Strong proficiency in Linux/Unix environments.
- Provide hands-on support for users running HPC/AI/ML workloads on systems.
- Deploy, validate, configure scientific / modeling / AI or simulation software & libraries. Ensuring dependencies, build systems, portability across nodes / GPU vs CPU etc. Port, build, test, and deploy HPC applications on Linux-based HPC systems.
- Assist researchers with job scripting, parallel scaling, and debugging of application issues.
- Collaborate with system administrators to install and maintain application software stacks and libraries (e.g., MPI, compilers, math libraries).
- Provide application support: help users get their code working on the HPC system; debug and resolve builds/execution issues.
- Assist in user training / documentation: helping users understand how to use the HPC resources efficiently (how to submit jobs, estimate resources, understand where bottlenecks are).
- Experience on HPC libraries (MKL, FFTW, HDF5, NetCDF, etc.).
- Experience in scripting or programming language (Python, Bash,



C/C++, Fortran).
- Escalate complex issues to L3 support with clear logs and diagnostics.
- Create/Provide basic documentation and training to onboarding for HPC AI resources.

Technical Skills

- Good understanding at OS level - RedHat, Ubuntu, SuSE etc.
- Good understanding on SLURM/PBS/LSF/Gridengine Schedulers.
- Good experience in deploying and optimizing and benchmarking scientific codes (WRF, OpenFOAM, LAMMPS, GROMACS, Quantum Espresso, VASP, NAMD, BLAST, GATK, Ansys, Abaqus, MATLAB, LS‑DYNA, Nastran, CAE/CFX) etc.
- Compiler & Library Optimization - Advanced user of Intel OneAPI, AOCC, NVIDIA HPC SDK, GNU, LLVM, PGI compilers, and MPI libraries (OpenMPI, MPICH, Intel MPI). Deep profiling insights via Nsight, VTune, PAPI.
- Proficient in application installation through SPACK software manager.
- Proficient on container technologies and orchestration tools - docker, singularity, Apptainer, Kubernetes.
- Valuable Knowledge in automation / scripting for repetitive tasks (shell scripts, Python etc.).
- Experience with containerization in HPC (Singularity, Docker, Apptainer and Kubernetes).
- Experience on GPU-accelerated computing (CUDA, ROCm, DOCA).
- Maintain documentation for supported applications, modules, best practices, and FAQs.
- Evaluate and support new HPC tools and technologies relevant to end-user applications.

Requirements

Job Requirements Work Location - Bangalore Should be supporting L3 level

Open for Client visits/field support.

📌 HPC Admin (Bengaluru)
🏢 SHI Solutions India
📍 Bengaluru