jobs

Senior Software Architect, AI Networking

NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. It’s a unique legacy of innovation that’s fueled by excellent technology—and amazing people. Today, we’re tapping into the unlimite

Company

NVIDIA

Location

Israel, Yokneam; Israel, Tel Aviv

Status

Open

Posted

2026-09-09T00:00:00+00:00

NVIDIA's E2E Architecture group is hiring a senior software architect for LLM inference at scale, working on multi-node deployments across GPU clusters. The role covers architecture for latency, throughput and cost, plus prototyping around KV cache handling, tensor and pipeline parallelism, and dynamic batching, and integrating networking work such as load balancing and congestion control. Requirements include a degree in computer science or electrical engineering, eight-plus years in distributed systems or performance-critical software, C++ and/or Python, and familiarity with CUDA. Two on-site locations are listed.