HPC Performance Engineer: Optimize CUDA/OpenMP on GPUs

NVIDIA

Portland (OR)

On-site

USD 152,000 - 241,500

Full time

14 days+

Get more replies from employers

Send a job-specific resume in minutes.

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a HPC Performance Engineer for the NVHPC compilers & tools group in Portland. You will analyze HPC applications to drive compiler optimizations and library enhancements, from single-core benchmarks to multi-node multi-GPU workloads.

You’ll work with compiler development and application engineering teams to deliver effective solutions, porting apps to different platforms and evaluating NVHPC components. Base salary ranges from 152,000 USD to 241,500 USD with equity and benefits.

Qualifications

BS/MS or equivalent experience in Computer Science or a related engineering field.
5+ years of programming experience.
Strong understanding of Fortran, C, C++, and programming techniques for parallel architectures, preferably for compilers.
Experience with OpenACC, OpenMP, MPI, CUDA and Standard Language Parallelism.
Strong skills in performance analysis and tuning and understanding of runtime environments.
Strong mathematical fundamentals, including linear algebra and numerical methods.
Excellent written and verbal communication in a dynamic team setting.

Responsibilities

Analyze the effect of different compilers and compiler optimizations on HPC application performance.
Evaluate whether and how the compiler and runtime can improve performance on CPU and CPU/GPU platforms.
Communicate limits of compiler capabilities with application engineering to guide improvements.
Port HPC applications to different platforms and programming models.
Evaluate the impact of NVHPC components, device driver, and system configuration on performance.