Senior GPU Architect - Performance and Yield Optimization

Details

NVIDIA is seeking a GPU architect to shape architectures that improve product yield while maintaining performance and architectural simplicity. The role focuses on analyzing manufacturing defects, optimizing architectural configurations, and developing approaches for multi-die architectures.

Responsibilities

• Shape GPU architectures that improve product yield while maintaining performance and architectural simplicity.
• Analyze how manufacturing defects affect architectural resources and develop methods to isolate or disable affected regions while preserving useful functionality.
• Build software tools and models that capture architectural, performance, and product requirements as rules and constraints.
• Develop efficient optimization techniques to explore large configuration spaces and identify viable product configurations.
• Develop approaches for multi-die architectures that improve utilization of available silicon while meeting product and performance requirements.
• Evaluate yield, performance, area, implementation cost, complexity, and product flexibility.
• Work across architecture, performance, design, silicon, Operations, and software teams to move selected proposals into production.

Requirements

• Bachelor's, master's, or doctoral degree in Computer Engineering, Computer Science, Electrical Engineering, or a related field, or equivalent experience.
• 10 or more years of experience in GPU, CPU, SoC, or complex processor architecture.
• Strong understanding of GPU architecture, the overall execution pipeline, and interactions across major GPU subsystems.
• Strong computer architecture fundamentals and the ability to reason about disabling, isolating, or reconfiguring resources.
• Strong C++ and/or Python skills, with experience building architectural models, simulators, optimization frameworks, or engineering analysis tools.
• Experience translating architecture and product requirements into rules, constraints, algorithms, and executable analysis, including complex optimization or configuration problems.
• Ability to quantify performance, product yield, area, cost, and complexity tradeoffs and influence decisions across architecture, design, implementation, and product teams.

Preferred Qualifications

• Hands-on GPU architecture or large-scale SoC architecture experience.
• Experience with constraint-based reasoning, combinatorial optimization, mathematical optimization, or related techniques.
• Background with silicon yield, defect tolerance, harvesting, redundancy, repair, resource isolation, or configurable processor architectures.
• Experience with multi-die, chiplet, or other modular processor architectures and complex resource-allocation problems.
• Experience using silicon or manufacturing data, developing performance or architecture simulators, profiling GPU workloads, or carrying concepts into production silicon.

Compensation and Benefits

The base salary range is USD 184,000–287,500 for Level 4 and USD 224,000–356,500 for Level 5. Compensation is determined based on location, experience, and the pay of employees in similar positions. The role is also eligible for equity and benefits.

Applications will be accepted at least until September 19, 2026. NVIDIA uses AI tools in its recruiting processes and is an equal opportunity employer.