Architect - GPU Performance
NVIDIA · Posted Sep 13
Graphics processing units, artificial intelligence platforms, accelerated computing, and data center solutions
Get a personal compatibility score
Add a resume for personal matches
About the role
NVIDIA is driving innovation at the intersection of visual processing, high performance computing and artificial intelligence, and is seeking passionate, highly motivated, creative engineers to join its HW architecture team. The team works on high performance CPU and Memory sub-systems, next-generation GPUs, and NoC-based interconnect fabric for visual computing, automotive, GPU, and HPC systems. As Architect - GPU Performance, you will perform system-level performance and bottleneck analysis of complex GPUs and SoCs and work closely with architecture and design teams to explore performance, area, and power trade-offs.
What you will do
- System level performance analysis/ bottleneck analysis of complex, high performance GPUs and System-on-Chips (SoCs).
- Work on hardware models of different levels of abstraction, including performance models, RTL test benches ,emulators and silicon to analyze performance and find performance bottlenecks in the system.
- Understand key performance use-cases of the product. Develop workloads and test suits targeting graphics, machine learning, automotive, video, compute vision applications running on these products.
- Work closely with the architecture and design teams to explore architecture trade-offs related to system performance, area, and power consumption.
- Develop required infrastructure including performance models, testbench components, performance analysis and visualization tools.
- Drive methodologies for improving turnaround time, finding representative data-sets and enabling performance analysis early in the product development cycle.
Skills used in this role
What the employer is looking for
- BE/BTech, or MS/MTech in relevant area, PhD is a plus, or equivalent experience.
- 3+ years of experience with exposure to performance analysis and complex system on chip and/or GPU architectures.
- Strong understanding of System-on-Chip (SoC) architecture, graphics pipeline, memory subsystem architecture and Network-on-Chip (NoC)/Interconnect architecture.
- Expert hands on competence in programming (C/C++) and scripting (Perl/Python). Exposure to Verilog/System Verilog, SystemC/TLM is a strong plus.
- Strong debugging and analysis (including data and statistical analysis) skills, including use for RTL dumps to debug failures.
Preferred qualifications
- Hands on experience developing performance simulators, cycle accurate/approximate models for pre-silicon performance analysis is a strong plus.
Benefits and support
- Compensation and benefits are detailed in the job posting
About NVIDIA
NVIDIA Corporation is a multinational technology company that designs graphics processing units (GPUs) for the gaming and professional markets, as well as system on a chip units (SoCs) for the mobile computing and automotive market. Pioneering accelerated computing, the company has become a driving engine of modern artificial intelligence, deep learning, and data center infrastructure.
- Industry
- Semiconductors
- Company size
- 42000+ employees
- Founded
- April 5, 1993
- Location
- Santa Clara, California, USA
- Funding stage
- Public Company
Funding
Public Company · $5M raised
Leadership
Founder, President and Chief Executive Officer
Executive Vice President and Chief Financial Officer
Founder and NVIDIA Fellow
Executive Vice President, Worldwide Field Operations
Recent coverage
NVIDIA Newsroom
NVIDIA Announces $1 Billion Commitment to Advance U.S. Super Intelligence Research and Quantum Leadership2026-10-08
NVIDIA Newsroom
NVIDIA Board of Directors Authorizes an Additional $150 Billion for Share Repurchases2026-10-03
NVIDIA Newsroom
NVIDIA Launches Open Agent Safety Platform to Secure Agents From Testing to Deployment2026-09-28
NVIDIA Newsroom
NVIDIA Reports Second Quarter Fiscal 2027 Financial Results with Record Revenue2026-08-26