Distinguished Software Architect - Deep Learning and HPC Communications

NVIDIA, a pioneer in GPU technology and AI innovation, is seeking a Distinguished Software Architect to join their GPU Communications Libraries and Networking team. This role focuses on developing cutting-edge communication libraries like NCCL, NVSHMEM, and UCX for Deep Learning and HPC applications. The position requires expertise in high-performance computing, working with systems that scale to thousands of GPUs connected through high-speed interconnects. The ideal candidate will help shape the future of data center platforms, pushing the boundaries of communication performance between GPUs.

The role combines deep technical expertise with strategic vision, requiring 15+ years of experience and a PhD in Computer Science or related field. You'll be responsible for researching new communication technologies, co-designing solutions with hardware and software teams, and driving the adoption of these technologies across different application verticals. The position demands expertise in parallel programming models, GPU architecture, and high-performance networking.

Working at NVIDIA means joining one of technology's most desirable employers, with opportunities to influence industry standards and contribute to open-source software. The company offers competitive compensation including a base salary range of $308,000 - $471,500, plus equity and benefits. This is an exceptional opportunity for a technical leader to impact the future of AI and HPC computing while working with some of the industry's brightest minds.