GPU Cloud Systems Architect - Performance & AI, Equity

NVIDIA; Santa Clara (CA); On-site; USD 224,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a GPU System Performance Architect in Santa Clara to design and optimize GPU-accelerated cloud computing systems. You will develop innovative processor and system architectures and analyze performance, cost and efficiency in large-scale data centers.

The role requires a Masters or PhD in a relevant field with 10 years of experience, strong math and communication skills, and expertise in computer architecture.

Qualifications

• Masters or PhD in Computer Science, Electrical Engineering, or Computer Engineering (or equivalent) with 10 years of relevant work or research experience.
• Excellent mathematical and analytical skills.
• Deep knowledge of computer architecture.
• Strong communication, organizational and interpersonal skills and team orientation.
• Experience with analytical performance modeling, simulation, profiling and analysis.

Responsibilities

• Develop innovative processor and system architectures for GPU-accelerated cloud computing.
• Analyze trade-offs in system performance, cost and efficiency using analytical models, simulators and data visualization tools.
• Understand and analyze interactions between hardware and software in large-scale data center deployments.
• Collaborate with software, product and business teams to guide direction of GPU-accelerated cloud computing.

Skills

Analytical skills

Communication

Teamwork

Mathematical skills

Education

Masters or PhD in CS/EE/CE

Job description

NVIDIA is seeking a GPU System Performance Architect in Santa Clara to design and optimize GPU-accelerated cloud computing systems. You will develop innovative processor and system architectures and analyze performance, cost and efficiency in large-scale data centers.

The role requires a Masters or PhD in a relevant field with 10 years of experience, strong math and communication skills, and expertise in computer architecture.