below marketmost similar roles pay hereabove market
This listing doesn't post a salary. Most similar roles pay
$196,750–$253,587.
Based on 240 similar postings.
Employer
About Nvidia
Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing
Nvidia currently has
1623 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 1110 roles with salary data.
The Senior Compute Kernel Architect, GPU Power joins the team responsible for the core GPU performance and power stack. In this role, you will design and develop CUDA kernels and infrastructure to exercise worst-case power behavior across compute, memory, and I/O subsystems. You will profile workloads to analyze the relationship between kernel behavior, hardware utilization, and power consumption while building workloads that generate controlled steady-state and transient power conditions. You will collaborate with architects and silicon validation engineers to characterize workload patterns and support power-stress methodology from pre-silicon modeling through post-silicon bring-up. Required skills include CUDA programming, PTX or assembly level development, and proficiency with Nsight Compute, Nsight Systems, and nvprof. You must understand streaming multiprocessors, execution pipelines, memory hierarchy, and power states.
Design and develop CUDA kernels to exercise worst-case power behavior across GPU compute, memory, and I/O subsystems.
Profile workloads to analyze the relationship between kernel behavior, hardware utilization, performance, and power consumption.
Build workloads that generate controlled steady-state and transient power conditions across multiple GPU architectures.
Identify functional units and workload patterns requiring additional characterization in partnership with GPU and silicon teams.
Support power-stress methodology from pre-silicon modeling and simulation through post-silicon bring-up and validation.
Optimize GPU kernels using PTX or assembly level programming to meet specific performance and power targets.
What we're looking for
MS or PhD in Computer Science, Electrical Engineering, Computer Engineering, or equivalent practical experience.
5+ years of experience in CUDA programming, GPU kernel development, high-performance computing, or performance architecture.
Hands-on experience developing and optimizing GPU kernels, including work at the PTX or assembly level.
Experience with GPU performance-analysis tools such as Nsight Compute, Nsight Systems, nvprof, or equivalent tools.
Strong understanding of GPU build principles, including streaming multiprocessors, execution pipelines, memory hierarchy, synchronization, occupancy, and power states.
Excellent analytical, debugging, and communication skills.
Experience crafting GPU power-stress microbenchmarks or test-to-failure workloads (preferred).
Familiarity with Power Delivery Network concepts, including package and board-level behavior, impedance, inductance, decoupling, resonance, voltage droop, and overshoot (preferred).
Remote (Santa Clara, CA)+336 days ago
$184,000–$287,500
GPU Architecture
Memory Systems
CUDA
PPA) analysis
RTL Simulation
Emulation
Verilog
VHDL
C
C++
Ansys Power Artist
Synopsys PTPX
Hardware Design
Scripting Languages
C
C++
Python
CUDA
GPU Architecture
x86
ARM
Kernel-mode Drivers
Performance Profiling
Hardware-Software Co-design
Device Driver Development
SoC
SDKs
Data Collection
Networking
High Performance Computing
Deep Learning
GPU Architecture
Parallel Computing
C
C++
Python
Perl
RTL
Graphics Algorithms
High Performance Computing
Signal Processing
Database
Test Infrastructure
Computer Architecture