GPU Profiling & Performance Tools Engineer — Nsight Equity

NVIDIA; Santa Clara (CA); On-site; USD 152,000 - 287,500; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a system software engineer to develop performance analysis capabilities for GPU developers and to co-design foundational software libraries. You will work across the Nsight toolset and NVIDIA hardware to enable high-fidelity events, counters, and test frameworks.

The role emphasizes hands-on work at multiple layers of NVIDIA’s technology, with collaboration across hardware architecture teams and a focus on performance triage and driver-like tooling.

Qualifications

• BS in EE/CS (or equivalent experience) with 5+ years, or MS with 2+ years, or PhD.
• Strong programming in C, C++, and Python.
• Good understanding of low-level assembly code.
• Knowledge of hardware pipeline concepts and co-design principles.
• Experience with performance analysis and optimization on hardware accelerators.
• Experience with simulators and emulators.
• Excellent problem-solving and team collaboration skills.
• Strong written and verbal communication skills.

Responsibilities

• Design, develop, and maintain GPU performance foundation libraries for Nsight tools focusing on hardware events and counters.
• Develop and implement GPU assembly tests.
• Build and maintain a test validation framework in CUDA and GPU Assembly.
• Use emulators to debug and verify instruction events.
• Document tools use cases and data workflows to aid architectural explorations.

Skills

C

C++

Python

CUDA

Assembly

Performance analysis

Education

BS EE/CS

MS/PhD

Tools

Nsight Tools

GPU Simulators

Emulators

Job description

NVIDIA is seeking a system software engineer to develop performance analysis capabilities for GPU developers and to co-design foundational software libraries. You will work across the Nsight toolset and NVIDIA hardware to enable high-fidelity events, counters, and test frameworks.

The role emphasizes hands-on work at multiple layers of NVIDIA’s technology, with collaboration across hardware architecture teams and a focus on performance triage and driver-like tooling.