Join NVIDIA, a leader in groundbreaking AI, High-Performance Computing, and Visualization, and contribute to the evolution of GPUs and SoCs. This role offers a unique opportunity to impact cutting-edge hardware and software that power the most exciting trends in modern computing. We are seeking creative architects passionate about performance and system architecture to drive scalable improvements across AI/ML, automotive, gaming, and HPC products.

Leverage your expertise in processor and system architecture performance to make a significant difference. You'll work on complex, high-performance systems, analyzing and optimizing bottlenecks. This is a chance to be at the forefront of innovation, shaping the future of parallel computing.

Analyze and identify performance bottlenecks in complex, high-performance GPUs and System-on-Chips (SoCs).

Utilize hardware models at various levels of abstraction, including performance models, RTL test benches, and emulators, to pinpoint system performance issues.

Collaborate closely with architecture and design teams to evaluate architecture trade-offs concerning system performance, area, and power consumption.

Understand and define key product performance use cases. Develop targeted workloads and test suites for graphics, machine learning, automotive, video, and compute vision applications.

Drive methodologies to reduce turnaround time, identify representative datasets, and enable early performance analysis in the product development lifecycle.

Develop essential infrastructure, including performance simulators, testbench components, and analysis tools.

We are looking for candidates with a BE/B.Tech or MS/M.Tech, or equivalent experience, with a PhD being a plus. A minimum of 2 years of relevant experience in system-level architecture and performance issues is required.

Possess a strong understanding of System-on-Chip (SoC) architecture, graphics pipeline, CPU architecture, memory subsystem architecture, and Network-on-Chip (NoC)/Interconnect architecture. Proficiency in C/C++ and scripting languages like Bash, Perl, or Python is essential.

Demonstrate strong debugging and analysis skills, including data and statistical analysis, with experience using RTL dumps for debugging. Familiarity with Verilog/System Verilog and SystemC/TLM is advantageous.

Exposure to performance simulators, cycle accurate/approximate models, or emulators for pre-silicon performance analysis is a plus. Excellent communication, organization, and global team collaboration skills are vital.