Energy HPC CUDA Performance Engineer

NVIDIA Gruppe; Zürich; Vor Ort; CHF 140.000 - 200.000; Vollzeit

Zusammenfassung

NVIDIA seeks a compute dev tech focused on accelerating energy simulation and AI workflows. You will optimize CUDA workloads, profile performance, and collaborate with customer and internal teams to deliver speedups on multi-GPU, multi-node systems.

Applicants should have 5+ years in GPU/HPC optimization, strong C/C++ and Python, and experience with Nsight tools. On-site role in Zürich, Switzerland with opportunities to influence NVIDIA’s energy and HPC roadmap.

Qualifikationen

• BS/MS (or equivalent) in CS/CE/EE/Physics/Applied Math or related field.
• Strong programming skills in C/C++ and Python on Linux.
• Hands-on experience with CUDA programming and GPU performance optimization concepts.
• Experience profiling and debugging performance using tools such as NVIDIA Nsight Systems / Nsight Compute (or equivalent).
• Understanding of parallel computing and performance fundamentals (vectorization, threading, NUMA, memory bandwidth/latency).
• Ability to communicate technical findings clearly to both engineers and non-engineers.
• 5+ years relevant experience in GPU/HPC optimization; strong track record of delivered speedups and scaling improvements.

Aufgaben

• Profile, analyze, and optimize GPU-accelerated applications with emphasis on CUDA kernels, memory movement, concurrency, and end-to-end throughput.
• Drive performance improvements across the stack: CUDA C++ kernel optimization, launch configuration, memory hierarchy, streams/events; GPU libraries (cuBLAS, cuFFT, cuSPARSE, cuSOLVER, NCCL); multi-GPU and multi-node scaling using MPI + NCCL, CPU/GPU overlap, communication patterns.
• Build reproducible benchmarks, performance reports, and tuning recommendations (before/after, methodology, scaling curves).
• Develop and maintain reference implementations, examples, and/or patches to customer code to enable performance and portability.
• Support customer engagements (POCs to production), including debugging correctness/performance issues and advising on best practices for deployment (containers, schedulers, clusters).
• Collaborate with internal teams to file actionable issues, validate fixes, and influence roadmap based on real customer requirements in Energy.
• Build internal libraries and reusable code that would lead to future NVIDIA products.

Kenntnisse

CUDA programming

C/C++

Python

GPU performance optimization

Nsight Systems

Nsight Compute

MPI

NCCL

memory bandwidth/latency

Ausbildung

BS/MS in CS/CE/EE/Physics/Applied Math or related field

Tools

cuBLAS

cuFFT

cuSPARSE

cuSOLVER

NCCL

MPI

Docker

Slurm

Jobbeschreibung

NVIDIA seeks a compute dev tech focused on accelerating energy simulation and AI workflows. You will optimize CUDA workloads, profile performance, and collaborate with customer and internal teams to deliver speedups on multi-GPU, multi-node systems.

Applicants should have 5+ years in GPU/HPC optimization, strong C/C++ and Python, and experience with Nsight tools. On-site role in Zürich, Switzerland with opportunities to influence NVIDIA’s energy and HPC roadmap.