Senior AI Networking Engineer - High-Performance Inference

NVIDIA Corporation; United States; Remote; USD 140,000 - 210,000; Full time

Benefits offered by this job

Generous benefits package

Competitive salary

Job summary

NVIDIA in the United States is seeking an enthusiastic software engineer to join our AI networking acceleration team to advance a groundbreaking open‑source library, leveraging hardware offloads, GPU kernels and RDMA networking.

You will develop a highly optimized inference framework, running on the world’s largest data centers, tackling performance, scalability and feature challenges in a dynamic, innovative environment at the forefront of technology.

Qualifications

• BS/equivalent in Computer Science or Software Engineering.
• 6+ years of experience in modern C/C++/Rust development.
• 3+ years of Linux environment experience with development tools.
• Deep knowledge of the TCP/IP network stack.
• Understanding of computer architecture and OS concepts.

Responsibilities

• Develop a highly optimized inference framework.
• Run on large-scale data centers and supercomputers.
• Contribute to a performance-oriented open-source library with GPU offloads and RDMA networking.

Skills

C/C++/Rust development

Linux development

TCP/IP networking

Computer architecture & OS concepts

Education

B.Sc. in CS or CE

Tools

CUDA kernels

Job description

NVIDIA in the United States is seeking an enthusiastic software engineer to join our AI networking acceleration team to advance a groundbreaking open‑source library, leveraging hardware offloads, GPU kernels and RDMA networking.

You will develop a highly optimized inference framework, running on the world’s largest data centers, tackling performance, scalability and feature challenges in a dynamic, innovative environment at the forefront of technology.