Senior Solutions Architect

Job Summary

To support the AI inference industry, the full-time Senior Solutions Architect will work remotely or onsite, collaborating with inference service providers to enhance performance, optimize systems, and provide technical leadership on cutting-edge inference technologies.

Key responsibilities

• Engage with inference partners to showcase the value of NVIDIA's stack and gather product insights for industry advancement
• Develop and manage inference recipes using tools like NVIDIA Dynamo to optimize GPU task distribution
• Guide customers and internal teams in deploying disaggregated inference systems while resolving complex technical challenges

Required qualifications

• 6+ years in Solutions Architecture or similar roles, with 2+ years focused on AI workloads in Kubernetes environments
• Experience with NVIDIA Dynamo, Triton Inference Server, or TensorRT-LLM for model optimization
• Strong knowledge of modern inference practices, including disaggregated serving and custom inference kernels
• Hands-on experience in full-stack agent design and modern memory and retrieval systems
• BS in Computer Science, Engineering, or equivalent experience