Senior System GPU Performance Engineer
Salary not listed • China, Shanghai • Full-time
Posted 1mo ago
About the job
NVIDIA is seeking a Senior System GPU Performance Engineer to join their Silicon Co-Design Group. This role focuses on maximizing the performance and power efficiency of production GPU systems by analyzing workload behavior, silicon capabilities, software policies, and platform constraints. You will be responsible for identifying bottlenecks and implementing improvements, owning the entire process from hypothesis to root-cause closure and product impact. This is a hands-on role that turns complex system data into faster, more efficient, and predictable products.
Responsibilities
- Own system-level GPU performance and power characterization from first silicon through production.
- Drive performance and power feature productization by translating measured behavior into firmware, driver, BIOS, platform, and silicon recommendations.
- Design experiments, execute test plans, and build models to isolate bottlenecks across GPU compute, memory, interconnect, CPU interaction, power delivery, and thermal limits.
- Analyze production-silicon data to quantify performance-per-watt trade-offs and identify optimization opportunities.
- Lead multi-functional root-cause closure across various teams and own fixes through confirmation.
- Establish reusable automation, visualization, and closed-loop methodologies to improve analysis and debug velocity.
- Translate complex system signals into decision-ready options for executive leadership.
Requirements
- BS or MS in Electrical Engineering, Computer Engineering, Computer Science, Systems Engineering, or related field (or equivalent experience).
- 8+ years of experience in GPU or system performance engineering, post-silicon characterization, silicon productization, or hardware-software performance optimization.
- Hands-on experience with silicon bring-up, frequency and power characterization, product binning, and performance-per-watt optimization.
- Strong understanding of GPU and system architecture, including compute pipelines, memory hierarchy, interconnects, CPU-GPU interactions, scheduling, and telemetry.
- Proven ability to design controlled experiments, develop performance or power models, analyze large datasets, and use statistics to identify bottlenecks.
- Strong programming and analysis skills using Python and one or more of C, C++, SQL, JMP, or equivalent.
- Demonstrated ability to structure ambiguous system-level problems and drive them to root-cause closure across globally distributed, multi-functional teams.
- Strong written and verbal communication skills, with the ability to translate complex technical issues into clear options for executive leadership.
Benefits
- Competitive benefits
- Continuous learning opportunities