Hybrid Senior HPC Applications Engineer

at NVIDIA

• Job title: Senior HPC Applications Engineer
• Job type: Full Time
• Experience level: Senior
• Salary: $224,000 - $356,500 per year
• Degree requirement: Bachelor's Degree
• Tech skills: Ansible, Docker, Jenkins, Kubernetes, Linux
• Location requirements: Hybrid, United States

About the role

• Senior HPC Application Engineer working at the intersection of scientific research and quantum technologies for NVIDIA. Ensure advanced applications run efficiently on the hybrid quantum-classical platform.

Responsibilities

• Collaborate with quantum and domain scientists to install, configure, compile, and optimize research applications on the HPC + quantum environment.
• Profile and tune performance for GPU-accelerated and hybrid workloads using tools such as NVIDIA Nsight, nvprof, and CUDA-Q profilers.
• Optimize job execution and resource utilization via Slurm policies, GPU partitioning, and hybrid orchestration between classical and quantum nodes.
• Develop and maintain containerized environments (Singularity, Kubernetes, or Docker) to ensure reproducible builds and easy deployment.
• Advise researchers on parallelization strategies, CUDA kernels, MPI configurations, and scaling behaviors.
• Work with system engineers to validate firmware, driver, and library configurations that maximize application performance (e.g., CUDA, cuQuantum, cuBLAS, NCCL).
• Integrate quantum SDKs and simulators (e.g., CUDA-Q, Qiskit, or IonQ/QuEra APIs) into HPC workflows.
• Establish performance baselines and benchmarking suites for GPU and hybrid workloads; publish metrics and dashboards.
• Support and train users — from onboarding and code migration to advanced performance debugging.
• Contribution to architecture evolution by providing feedback on workload patterns, bottlenecks, and future capacity planning.

Requirements

• 12+ years of experience in HPC application performance engineering, computational science, or scientific software development.
• Strong background in GPU programming (CUDA, cuQuantum, CUDA-Q) and parallel programming (MPI, OpenMP).
• Proficiency with Linux, Slurm, containerization, and CI/CD pipelines (GitHub, Jenkins, Ansible, or GitLab CI).
• Experience in profiling, benchmarking, monitoring, and optimizing scientific or AI/ML applications on multi-GPU systems.
• Working knowledge of NVIDIA HPC SDK, CUDA-Q, or cuQuantum stack.
• Bachelor’s or Master’s degree (or equivalent experience) in Computer Science, Physics, Applied Mathematics, or Engineering (PhD a plus).
• Excellent communication and collaboration skills to support a multidisciplinary research community.

Benefits

• equity
• benefits