CUDA Deep Learning Systems Architect

NVIDIA; Austin (TX); On-site; USD 224,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking a seasoned software professional to work at the intersection of CUDA and Deep Learning Systems, driving innovations from kernels to cluster-scale AI systems. You will help maximize hardware performance for emerging AI workloads, collaborating with researchers and architects to push accelerator compute utilization and memory bandwidth.

Join a highly technical, research-oriented team focused on model optimization, custom kernel development, and scalable AI infrastructure,

Qualifications

• BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or related field (or equivalent).
• 8+ years of relevant industry experience or equivalent academic experience after degree.
• Strong proficiency in C++ and Python programming.
• Solid background in the fundamentals of Deep Learning with a focus on transformers.
• Strong understanding of distributed computing principles, multi-node scaling, and the challenges of cluster-scale execution.
• Proven experience in systems programming, computer architecture, and low-level performance optimization.
• Familiarity with deep learning accelerator architectures such as the GPU and hands-on experience with CUDA programming, kernel optimization, and workload profiling.
• Experience profiling and optimizing generative AI models, including large language models.
• Research background in ML systems and experience profiling and optimizing innovative vision models, generative AI architectures, or diffusion models.
• Track-record of initiative and willingness to deep-dive on problems across the stack.

Responsibilities

• Explore, research, and prototype novel systems optimizations for advanced deep learning models at the intersection of high-level DL frameworks and low-level CUDA through modeling, simulation, and silicon prototyping.
• Architect and optimize distributed computing systems that scale from a single node to massive cluster-scale environments.
• Design, implement, and optimize custom high-performance CUDA kernels for emerging neural network architectures and workloads.
• Analyze hardware-software interactions to identify and resolve performance bottlenecks in training and inference pipelines.
• Collaborate with AI researchers, HW and SW architects, kernel and compiler authors and CUDA driver experts to co-design systems and algorithms that improve accelerator compute utilization, memory bandwidth, and cross-node communication efficiency.
• Develop exploratory tools and runtime systems to profile and accelerate new paradigms in deep learning.
• Write clean, maintainable code so prototypes can transition into open-source releases, upstream framework integrations, internal tools, or closed-source products.

Skills

C++

Python

Deep Learning

Transformers

Distributed computing

CUDA

Kernel optimization

Performance profiling

ML systems

Education

BS/MS/PhD in CS/CE/EE

Tools

NCCL

MPI

UCX

Triton

Job description

NVIDIA is seeking a seasoned software professional to work at the intersection of CUDA and Deep Learning Systems, driving innovations from kernels to cluster-scale AI systems. You will help maximize hardware performance for emerging AI workloads, collaborating with researchers and architects to push accelerator compute utilization and memory bandwidth.

Join a highly technical, research-oriented team focused on model optimization, custom kernel development, and scalable AI infrastructure,