Senior Solutions Architect – Large Scale Neural Networks Inference
NVIDIA United Kingdom
Defines and leads AI inference strategy for EMEA AI-native customers, guiding engagements from proof of concept to production-scale deployments. Architects and optimizes high-performance inference pipelines using NVIDIA Dynamo, TensorRT-LLM, vLLM and SGLang, tackling latency, cost per token, memory and networking bottlenecks while feeding deployment insights back into the product roadmap.