Senior CUDA Deep Learning Systems Engineer – Equity

Nvidia Corporation in; Santa Clara (CA); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits package

Job summary

NVIDIA seeks a Senior Software Engineer to advance CUDA Deep Learning Systems for finance-focused workloads. You will develop high-performance kernels, optimize distributed AI pipelines, and push hardware-software co-design across GPUs and clusters.

You will collaborate with AI researchers and HW/SW teams to improve accelerator utilization, memory bandwidth, and cross-node communication for transformer-based models at scale. Strong C++/Python and DL fundamentals required.

Qualifications

• BS/MS/PhD in Computer Science, Computer Engineering, Electrical Engineering or related field
• 8+ years of experience in industry or academia after degree
• Strong proficiency in C++ and Python
• Solid fundamentals in Deep Learning with transformers
• Distributed computing, multi-node scaling, and cluster performance
• Experience with CUDA programming, kernel optimization, and workload profiling
• Experience profiling generative AI models and large language models
• Research background in machine learning systems and related fields

Responsibilities

• Explore, prototype, and optimize systems at the intersection of AI and CUDA
• Architect and optimize distributed computing systems from node to cluster scale
• Design and optimize custom high-performance CUDA kernels
• Analyze hardware-software interactions to resolve performance bottlenecks
• Collaborate with AI researchers, HW/SW architects, kernel and compiler experts
• Develop profiling tools and runtimes for new DL paradigms
• Write clean, reusable code for prototypes and future integration

Skills

C++

Python

Distributed computing

CUDA programming

Kernel optimization

GPU architectures

Transformers

Multi-node scaling

Research

Education

BS/MS/PhD in CS/CE/EE

Tools

CUDA

NCCL

MPI

XLA

Triton

Job description

NVIDIA seeks a Senior Software Engineer to advance CUDA Deep Learning Systems for finance-focused workloads. You will develop high-performance kernels, optimize distributed AI pipelines, and push hardware-software co-design across GPUs and clusters.

You will collaborate with AI researchers and HW/SW teams to improve accelerator utilization, memory bandwidth, and cross-node communication for transformer-based models at scale. Strong C++/Python and DL fundamentals required.