Senior Solutions Architect, AI Inference

What you'll do

• Advise inference partners, share NVIDIA’s stack, and bring product insights back to internal teams.
• Build inference recipes and accelerate pipelines using serving backends, including for disaggregated inference.
• Promote DevOps best practices and provide technical leadership on deployment and complex issues.

What they ask for

• 6+ years in Solutions Architecture, Solution Engineering, Forward-Deployed Engineering, or similar, deploying distributed systems in customer engagements, including 2+ years with AI workloads on Kubernetes.
• Experience with one of NVIDIA Dynamo, Triton Inference Server, or TensorRT-LLM for model optimization and serving.
• Deep knowledge of modern inference practices, including 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, evaluation, skill design, and governance.

Nice to have

• Prior experience deploying NVIDIA inference technologies such as Dynamo, NIXL, and Grove.
• Experience with model customization techniques and related data curation, or contributions to relevant open-source projects.

Pay

184,000 USD - 287,500 USD base salary (Level 4); 224,000 USD - 356,500 USD base salary (Level 5)

Tools

NVIDIA Dynamo, Triton Inference Server, TensorRT-LLM, vLLM, SGLang, Kubernetes, NIXL, Grove

AI focus

Scale AI inference and token generation; optimize and serve models, deploy disaggregated inference, and design full-stack agents.