Distinguished Engineer, Scaled Out Inferencing

NVIDIA is a technology leader in accelerated computing for cloud and enterprise environments, advancing artificial intelligence, high-performance computing, and visualization. The Distinguished Engineer will lead the global strategy for scaled-out AI inferencing, architect distributed pipelines and model-serving systems, and drive full-lifecycle deployment, scaling, and operational reliability across enterprise and cloud environments.

Responsibilities:

• Various Architectural Work: Architect distributed pipelines, define and drive the technical implementation of high-throughput, low-latency, distributed inference systems to support massive-scale AI workloads
• Collaborate on Cross Domain Disciplines: Hardware-software co-optimization, drive performance tuning at the kernel and driver level, optimizing GPU resource management and hardware acceleration for production-grade model serving
• Collaborate on Open Source and Ecosystem Projects: Guide and influence open source projects Dynamo, TensorRT-LLM, and ecosystem projects (vLLM, SGLang, Linux, Kubernetes, Ray) to bring state of the art inferencing on NVIDIA accelerated hardware
• Accelerate Integration: Orchestrate model lifecycles, lead the strategy for full-lifecycle model management, including automated deployment, versioning, and intelligent scaling across varied cloud and datacenter environments
• Engage Stakeholders: Collaborate with customers, infrastructure providers, and partners to ensure NVIDIA’s solutions set the industry standard for performance and availability
• Full Software and System Lifecycle: From ideation to architecture, design, development, deployment, operations, and full lifecycle management, lead all technical aspects of planning and continuous evolution of a large technical scope