HPC Performance Engineer: Optimize GPU-Accelerated Apps

NVIDIA; France; On-site; EUR 90,000 - 150,000; Full time

Job summary

NVIDIA is seeking a senior HPC performance analyst to analyze and run HPC applications on NVIDIA HPC servers and systems, gaining insight into performance characteristics across distributed-memory, heterogeneous compute environments.

You will work with applications ranging from small synthetic benchmarks to full-scale distributed jobs, identifying optimization opportunities for compiler and applications engineering teams.

Qualifications

• BS/MS or equivalent in Computer Science or related engineering field.
• 8+ years of programming experience.
• Strong understanding of Fortran/C/C++, especially for parallel architectures.
• Experience with OpenACC, OpenMP, MPI, and CUDA.
• Strong skills in performance analysis and tuning, and broad understanding of parallel tools/runtime environments.
• Strong mathematical fundamentals including linear algebra and numerical methods.
• Excellent written and verbal communication skills.

Responsibilities

• Assist customers with GPU-accelerated HPC applications.
• Analyze HPC applications to understand performance characteristics.
• Provide advice to drive compiler and applications engineering development teams.
• Lead and manage projects is a plus.

Skills

Performance analysis

Parallel programming

Communication

Time management

Problem solving

Education

BS/MS or equivalent in Computer Science

Tools

OpenACC

OpenMP

MPI

CUDA

Job description

NVIDIA is seeking a senior HPC performance analyst to analyze and run HPC applications on NVIDIA HPC servers and systems, gaining insight into performance characteristics across distributed-memory, heterogeneous compute environments.

You will work with applications ranging from small synthetic benchmarks to full-scale distributed jobs, identifying optimization opportunities for compiler and applications engineering teams.