About the job
Join NVIDIA as a Senior Software Architect for AI Networking and help define the future of AI inference infrastructure. In this groundbreaking role, you will drive performance and scalability in distributed AI systems. You will focus on optimizing and innovating how large language models and generative AI workloads move and process data at scale.
Responsibilities
Research, design, and implement advanced AI networking technologies with an emphasis on accelerating inference workloads using NVIDIA Inference Xfer Library (NIXL)—a high-throughput, low-latency communication library for asynchronous, efficient data transfers across GPUs, CPUs, and various storage targets.
Collaborate with other teams across NVIDIA's hardware, software, and research units to co-design hardware-accelerated and software solutions for AI inference.
Own the creation of prototypes and solutions for next-generation AI inference systems.
Drive architectural decisions underpinning the deployment and scaling of AI inference using NVIDIA’s innovative technology.
Qualifications
Minimum
Master's or Ph.D. in Computer Science, Electrical or Computer Engineering (or equivalent experience).
At least 8 years of relevant academic or confirmed experience in the field.
Comprehensive understanding of AI workloads (primarily inference, but also training) and their impact on network infrastructure.
Strong proficiency in areas such as Machine Learning/Deep Learning fundamentals, inference runtimes, and Deep Learning frameworks.
Proficiency in C or C++ for systems software development; familiarity with Rust is an advantage.
Preferred
Familiarity with Rust is an advantage.