At NVIDIA, we are constantly reinventing the way computing is done. From pioneering the GPU and shaping the future of computer graphics to redefining parallel computing and artificial intelligence, our engineers are relentlessly pushing the boundaries of innovation. Join us to be part of a team that’s driving breakthroughs in performance, scalability, and intelligence—solutions that empower developers, researchers, and creators around the globe.
What you’ll be doing:
Conduct performance and bottleneck analysis of complex, high-performance GPUs.
Develop, validate, and maintain performance models and simulation tools at various levels of abstraction—including analytical, performance, and cycle-level models.
Collaborate closely with architects and design engineers to explore architecture trade-offs across performance, area, and power metrics.
Drive performance exploration and provide insights to guide feature definition and design decisions for next-generation GPU architectures.
Develop infrastructure and tools for performance data analysis, visualization, and validation to accelerate architecture studies.
Contribute to methodologies that enable early performance estimation and improve analysis turnaround time.
What we need to see:
BE/BTech or MS/MTech in Computer Engineering, Computer Science, or Electrical Engineering; PhD preferred.
5+ years in architecture or performance modeling, with exposure to GPUs or similar compute/graphics architectures.
Strong programming and modeling skills inC++and scripting expertise inPython.
Deep understanding ofcomputer architecture, including SoCs, graphics pipelines, memory systems, interconnects, and caches.
Experience inperformance analysis, modeling, or simulationat various levels of abstraction.
Hands-on experience ingraphics, GPU, or AI performance modeling/explorationis highly desirable.
Familiarity withhardware modeling and performance visualization frameworks is a strong plus.
Demonstrated strength in analysis, debugging, and extracting insights from performance data.
Ways to stand out from the crowd:
Proven experience building or maintaining GPU or AI hardware performance models.
Strong understanding of graphics or compute workloads and how architectural choices impact real-world performance.
Experience in data-driven performance optimization and tool development for architectural exploration.
Excellent communication and collaboration skills, with a track record of driving cross-functional initiatives.
