HPC Performance Architect - Multi-GPU Clusters

NVIDIA; Poland; On-site; PLN 221,250 - 383,500; Full time

Benefits offered by this job

Highly competitive salaries

Extensive benefits package

Diversity and inclusion promotion

Job summary

NVIDIA is seeking a Performance Engineer to lead performance characterization and analysis on large multi-GPU and multi-node clusters in Poland. Candidates should possess a M.S. or PhD in Computer Science or similar, with experience in performance benchmarking and parallel programming. The role involves debugging performance issues across the hardware/software stack and collaborating with dynamic teams. NVIDIA offers competitive salaries and an inclusive work environment.

Qualifications

• 3+ years of experience with parallel programming and at least one communication runtime.
• Experience conducting performance benchmarking and triage on large scale HPC clusters.
• Good understanding of computer system architecture and operating systems principles.

Responsibilities

• Conduct in-depth performance characterization on multi-GPU and multi-node clusters.
• Evaluate proof-of-concepts and conduct trade-off analysis.
• Triage and root-cause performance issues reported by customers.

Skills

Parallel programming

Performance benchmarking

HPC experience

Debugging performance issues

Scripting in Python

Education

M.S. or PhD in Computer Science

Tools

MPI

CUDA

Kubernetes

Docker

Job description

NVIDIA is seeking a Performance Engineer to lead performance characterization and analysis on large multi-GPU and multi-node clusters in Poland. Candidates should possess a M.S. or PhD in Computer Science or similar, with experience in performance benchmarking and parallel programming. The role involves debugging performance issues across the hardware/software stack and collaborating with dynamic teams. NVIDIA offers competitive salaries and an inclusive work environment.