Principal GPU Performance Engineer - CSP Engagements

NVIDIA; Santa Clara (CA); On-site; USD 272,000 - 431,250; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a Principal Engineer to lead performance efforts for CSP Engagements. Responsibilities include driving performance characterization and ensuring optimal integration with engineering teams. This role requires a deep understanding of GPU performance, strong analytical skills, and the ability to engage with customers effectively.

Applicants should have over 15 years of relevant experience, proficiency with GPU profiling tools, and the ability to articulate performance metrics to both technical and executive audiences. A commitment to customer satisfaction and continuous improvement is essential.

Qualifications

• 15+ years of experience in systems performance engineering, ideally in GPU/HPC/ML infrastructure.
• Proficiency in GPU workload profiling tools.
• Strong data analysis and visualization skills (Python, pandas).
• Ability to communicate performance findings to technical audiences.

Responsibilities

• Drive performance characterization work streams with engineering teams.
• Gather and synthesize CSP performance feedback.
• Ensure key open-source performance and stress tools are validated.
• Conduct cross-CSP performance comparison and pattern analysis.
• Define test strategies and tooling requirements for performance validation.

Skills

GPU workload profiling

Statistical methods for performance analysis

Data analysis and visualization skills

Education

BS or MS in Computer Science, Computer Engineering, or related field

Tools

nsight systems

nsight compute

DCGM metrics

Job description

NVIDIA is seeking a Principal Engineer to lead performance efforts for CSP Engagements. Responsibilities include driving performance characterization and ensuring optimal integration with engineering teams. This role requires a deep understanding of GPU performance, strong analytical skills, and the ability to engage with customers effectively.

Applicants should have over 15 years of relevant experience, proficiency with GPU profiling tools, and the ability to articulate performance metrics to both technical and executive audiences. A commitment to customer satisfaction and continuous improvement is essential.