Senior AI Inference Architect — Disaggregated Kubernetes

NVIDIA; United States; Remote; USD 184,000 - 357,000; Full time

Job summary

NVIDIA is hiring an architect to reshape AI inference with disaggregated systems and scalable reference architectures. You will guide partners, design end-to-end inference pipelines, and optimize performance across GPU clusters at scale.

You will mentor teams, drive strong customer engagements, and contribute to the deployment of cutting-edge NVIDIA Dynamo, Triton Inference Server, and TensorRT-LLM based solutions. Equity and comprehensive benefits are provided.

Qualifications

• 6+ Years in Solutions Architecture driving customer engagements to deploy distributed systems and AI workloads.
• 2+ years with AI workloads on Kubernetes.
• Experience with NVIDIA Dynamo, Triton Inference Server, or TensorRT-LLM for model optimization/serving.
• Deep knowledge of disaggregated serving, multi-tier KV cache management, speculative decoding, quantization, and custom inference kernels.
• Hands-on full-stack agent design with modern sandboxing, memory and retrieval systems with evaluation, skill design and governance.

Responsibilities

• Work with inference partners to build and operate inference recipes and improve efficiency.
• Accelerate inference pipelines using TensorRT-LLM, vLLM, and other backends to integrate with disaggregated inference.
• Evangelize devops best-practices: Kubernetes clusters, compute fabrics, observability.
• Provide mentorship and technical leadership to customers and internal teams during deployment of disaggregated inference systems.

Skills

Solutions Architecture

Customer engagements

AI workloads on Kubernetes

Full-stack agent design

Mentorship & leadership

Education

BS in CS/Engineering

Tools

NVIDIA Dynamo

Triton Inference Server

TensorRT-LLM

Kubernetes

Disaggregated inference

Job description

NVIDIA is hiring an architect to reshape AI inference with disaggregated systems and scalable reference architectures. You will guide partners, design end-to-end inference pipelines, and optimize performance across GPU clusters at scale.

You will mentor teams, drive strong customer engagements, and contribute to the deployment of cutting-edge NVIDIA Dynamo, Triton Inference Server, and TensorRT-LLM based solutions. Equity and comprehensive benefits are provided.