NVIDIA is seeking a Performance Architect for Deep Learning Software at the senior level to join its cutting-edge Deep Learning Architecture team. This role involves validating and analyzing the performance of GPU-accelerated systems and software architectures, debugging deep learning and data analytics applications to identify performance bottlenecks, and developing scripts and tools for analysis and visualization using analytical models and simulators. The ideal candidate will collaborate with various NVIDIA teams, including CUDA and AI Compiler teams, AI/ML training and inference performance teams, and hardware architecture performance teams, to enhance system throughput and optimize critical deep learning layers. Candidates should have a Master’s or PhD in Computer Science, Electrical Engineering, or related fields, along with expertise in software design, parallel programming, computer architecture, and machine learning fundamentals. Proficiency in Python, C, and C++ is required, as well as experience with GPU computing and analytical performance modeling.
Skills
Python
C
C++
GPU
CUDA
Parallel_Programming
Performance_Analysis
Profiling
Machine_Learning
Deep_Learning
Computer_Architecture
High_Performance_Computing
Energy_Efficient_Designs
Analytical_Modeling
NVIDIA_CUDA
AI_Compiler
What you'll do
Validate and analyze performance of GPU-accelerated system architectures for deep learning.
Debug deep learning software to resolve performance bottlenecks and improve efficiency.
Develop scripts and tools for analyzing, visualizing, and debugging software using models and simulators.
Work with CUDA and AI Compiler teams to identify and fix performance issues in software.
Collaborate with hardware architecture teams to define expectations for new deep learning hardware features.
What we're looking for
Master's or PhD in Computer Science, Electrical Engineering, or related field.
Expertise in software design, debugging, and performance analysis.
Hands-on experience with parallel programming and GPU computing.
Strong understanding of computer architecture and performance optimization.
Fluency in Python, C, and C++ for developing and analyzing software.
Experience in machine learning fundamentals and high-performance computing.
Market check
Salary context
Below market
How this pay compares to similar roles
This role $160k
$110k
most similar roles pay here
$256k
This role pays less than
87%
of similar roles. Most pay
$181,758–$235,750
— the shaded band above.
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
825 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 813 roles with salary data.
Python
C
C++
CUDA
MPI
OpenMP
HPC
GPU
Deep Learning
Machine Learning
Performance Modeling
Systems Performance Analysis
AI Inference Workloads
CUDA Kernels
Custom ASIC Hardware