Join our dynamic, research-oriented team as a Senior Software Engineer specializing in CUDA and Deep Learning Systems to work on pioneering initiatives at the intersection of advanced deep learning architectures and distributed computing. You will explore novel system optimizations for high-level DL frameworks and low-level CUDA through modeling, simulation, and silicon prototyping, while also designing and optimizing custom high-performance CUDA kernels tailored to emerging neural network architectures. Your day-to-day involves analyzing complex hardware-software interactions, collaborating with AI researchers and architects, and developing exploratory tools to profile and accelerate new paradigms in deep learning. The role requires strong proficiency in C++ and Python, a solid background in Deep Learning fundamentals, and experience with CUDA programming and distributed computing principles. Ideal candidates have expertise in major DL frameworks like PyTorch and JAX, hands-on experience with communication libraries such as NCCL, and knowledge of numerical methods for low-precision arithmetic.
Skills
CUDA
Python
C++
PyTorch
JAX
TensorRT
vLLM
Nemo
Megatron
MaxText
Triton
XLA
NCCL
MPI
UCX
Docker
CI/CD
Git
GitHub
Linux
PostgreSQL
Prometheus
Grafana
What you'll do
Explore and prototype novel optimizations for advanced deep learning models using CUDA.
Design and optimize distributed computing systems for seamless scaling from single nodes to supercomputers.
Develop custom high-performance CUDA kernels for emerging neural network architectures.
Analyze hardware-software interactions to resolve performance bottlenecks in AI workloads.
Collaborate with experts to co-design systems that enhance accelerator compute utilization and efficiency.
Create tools and runtime systems to profile and accelerate new paradigms in deep learning.
Write maintainable code for exploratory prototypes transitioning into open-source or commercial products.
What we're looking for
8+ years of industry experience in software engineering or equivalent academic experience.
Strong proficiency in C++ and Python programming languages.
Solid understanding of deep learning fundamentals, particularly transformers.
Expertise in distributed computing principles and multi-node scaling challenges.
Proven experience in systems programming and low-level performance optimization.
Deep knowledge of CUDA programming and kernel optimization for GPUs.
Familiarity with major deep learning frameworks’ autograd, training, and inference internals.
Market check
Salary context
This
$184,000–$287,500
range sits above
81%
of similar postings on FindRole.
Peer median band
$162,500–$250,100
Median floor and ceiling across peers.
Typical midpoint (25–75%)
$196,750–$235,750
Middle half of comparable postings.
Based on 240 comparable postings.*
* 240 is the maximum number of comparable postings sampled.
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
801 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 797 roles with salary data.
Us, Ca, Santa Clara, US64 days ago
$152,000–$241,500
C
CUDA
Linux
Windows
macOS
C++
Python
Git
CI/CD
NVIDIA
Pre-Silicon
Simulation
Emulation
Kernel_Programming
Operating_Systems
Virtual_Memory
Threads
Process_Control
Large_Codebases
Documentation