Senior AI Inference Architect for Large-Scale LLMs

NVIDIA Corporation; France; Hybrid; EUR 120,000 - 190,000; Full time

Benefits offered by this job

Competitive compensation

Comprehensive benefits

Job summary

NVIDIA Corporation is seeking a Senior Solutions Architect to lead large-scale AI inference deployments across EMEA, defining technical direction and bottleneck strategies in collaboration with frontier labs and enterprise customers.

You will architect high-performance inference pipelines using Dynamo, TensorRT-LLM, vLLM and related backends, improve GPU utilization, and translate customer insights into product feedback that guides the NVIDIA stack.

Qualifications

• MS or PhD in Computer Science, Engineering or equivalent.
• 8+ years in AI/ML infrastructure with LLM/VLM inference optimization.
• Deep understanding of transformer inference acceleration and memory hierarchies.
• Proven ability to lead technical initiatives and communicate with teams.
• Experience deploying AI at scale in enterprise/ frontier labs.

Responsibilities

• Lead inference strategy for a portfolio of EMEA AI natives customers from PoC to production.
• Identify latency, memory, cost per token, and networking bottlenecks in deployments.
• Architect and optimize high-performance inference pipelines using NVIDIA stack.
• Translate customer insights into actionable product feedback for roadmap.

Skills

AI infrastructure

LLM inference

Production deployment

Latency optimization

Stakeholder communication

Education

MS or PhD in Computer Science or Engineering

Tools

Dynamo

TensorRT-LLM

vLLM

NIM

Kubernetes

Job description

NVIDIA Corporation is seeking a Senior Solutions Architect to lead large-scale AI inference deployments across EMEA, defining technical direction and bottleneck strategies in collaboration with frontier labs and enterprise customers.

You will architect high-performance inference pipelines using Dynamo, TensorRT-LLM, vLLM and related backends, improve GPU utilization, and translate customer insights into product feedback that guides the NVIDIA stack.