Senior CUDA DL Systems Engineer for Performance & Scale

NVIDIA; Town of Texas (WI); On-site; USD 224,000 - 357,000; Full time

Benefits offered by this job

Equity and benefits

Job summary

NVIDIA is seeking an experienced software professional to push the boundaries of CUDA and Deep Learning Systems. You will work on architectures bridging DL models and CUDA, from kernel optimization to cluster-scale AI workloads.

Join a research-oriented team focused on profiling, optimizing, and accelerating AI workloads across single GPUs to supercomputer clusters. Strong C++, Python, and deep learning fundamentals are essential for success.

Qualifications

• BS/MS/PhD in CS/CE/EE or related field (or equivalent experience).
• 8+ years of relevant industry or academic experience after degree.
• Strong proficiency in C++ and Python programming.
• Solid background in Deep Learning fundamentals with focus on transformers.
• Strong understanding of distributed computing and multi-node scaling.
• Experience in CUDA programming, kernel optimization, and workload profiling.
• Research background in ML systems or related fields with vision/diffusion/AI models.

Responsibilities

• Explore novel system optimizations for deep learning models at the intersection of DL and CUDA.
• Architect and optimize distributed systems from single node to cluster-scale environments.
• Design and optimize custom high-performance CUDA kernels for neural network architectures.
• Analyze hardware-software interactions to troubleshoot performance bottlenecks in training and inference.
• Collaborate with AI researchers, HW/SW architects, kernel/driver experts to improve utilization and memory bandwidth.
• Develop tools and runtimes to profile and accelerate new DL paradigms.
• Write clean, maintainable code and prepare prototypes for open-source or commercial integration.

Skills

C++

Python

Deep Learning

Transformers

Distributed Computing

CUDA

Kernel Optimization

Workload Profiling

Research Experience

Education

BS/MS/PhD in CS/CE/EE or related

Tools

NCCL

MPI

UCX

TensorRT

Triton

Torch Compile

Job description

NVIDIA is seeking an experienced software professional to push the boundaries of CUDA and Deep Learning Systems. You will work on architectures bridging DL models and CUDA, from kernel optimization to cluster-scale AI workloads.

Join a research-oriented team focused on profiling, optimizing, and accelerating AI workloads across single GPUs to supercomputer clusters. Strong C++, Python, and deep learning fundamentals are essential for success.