Senior System GPU Performance Engineer
Core
Maximize performance and power efficiency of production GPU systems by connecting workload behavior, silicon capability, software policy, and platform constraints to identify bottlenecks and productize improvements.
Role type
Senior System GPU Performance Engineer
Builds
Production GPU systems for Datacenter, Gaming, Robotics, Automotive, and Embedded markets
Domain
Hardware-software co-design, GPU architecture, and system performance optimization
Required skills
GPU/system architecture analysis, silicon bring-up, frequency and power characterization, product binning, performance-per-watt optimization, experimental design, statistical analysis, Python/C/C++/SQL programming, automation, root-cause analysis
Preferred skills
GPU profiling, workload characterization, production telemetry, performance counters, simulation-to-silicon correlation, reusable performance models, applied AI tools for experiment design
Technologies
Python, C, C++, SQL, JMP
Responsibilities
Own system-level GPU performance and power characterization from first silicon through production; Drive performance and power feature productization into firmware, driver, BIOS, and silicon recommendations; Design experiments and build models to isolate bottlenecks across compute, memory, interconnect, and thermal limits; Analyze production-silicon data to quantify performance-per-watt trade-offs; Lead multi-functional root-cause closure across architecture, design, validation, and manufacturing teams; Establish reusable automation and visualization methodologies; Translate complex system signals into decision-ready options for executive leadership
Seniority
Senior, hands-on IC
