Senior AI Inference Architect: Scale & Strategy

NVIDIA; United Kingdom; On-site; GBP 130,000 - 190,000; Full time

Job summary

NVIDIA is seeking a Senior Solutions Architect to lead large-scale neural network inference initiatives across EMEA. You will drive technical collaboration with frontier AI labs and enterprises, shaping the direction of AI inference deployments and optimizing pipelines for efficiency and latency.

You will guide customers from proof of concept to production-scale deployments, translating insights into product feedback and roadmaps for Dynamo, TensorRT-LLM, and NIM.

Qualifications

• MS or PhD in Computer Science, Engineering, or equivalent experience.
• 8+ years in AI/ML infrastructure with LLM/VLM inference optimization at scale.
• Deep knowledge of transformer inference acceleration and GPU memory hierarchies.
• Experience leading technical initiatives and communicating with research teams.

Responsibilities

• Lead the inference strategy for a portfolio of EMEA AI Native customers from PoC to production-scale deployments.
• Identify latency, efficiency, and cost challenges in real deployments and propose scalable solutions.
• Architect and optimize high-performance inference pipelines using NVIDIA Dynamo, TensorRT-LLM, and other backends.
• Translate deployment insights into actionable product feedback for NVIDIA stack roadmap.

Skills

LLM Inference

GPU Optimization

Production Deployment

Cross-team Leadership

Effective Communication

Education

MS or PhD in Computer Science/Engineering

Tools

NVIDIA Dynamo

TensorRT-LLM

vLLM

Kubernetes

NIM

Job description

NVIDIA is seeking a Senior Solutions Architect to lead large-scale neural network inference initiatives across EMEA. You will drive technical collaboration with frontier AI labs and enterprises, shaping the direction of AI inference deployments and optimizing pipelines for efficiency and latency.

You will guide customers from proof of concept to production-scale deployments, translating insights into product feedback and roadmaps for Dynamo, TensorRT-LLM, and NIM.