EMEA AI Inference Architect: Scale LLM Deployments

NVIDIA Corporation; France; À distance; EUR 68 000 - 151 000; Plein temps

Avantages offerts par ce poste

Competitive salary

Comprehensive benefits

Equal opportunity employer

Résumé du poste

NVIDIA is seeking a Senior Solutions Architect to lead large-scale AI inference across EMEA, collaborating with frontier labs and enterprises to deploy AI at scale. You will define technical direction, optimize inference pipelines, and drive adoption of NVIDIA technologies across customer environments.

The role requires 8+ years in AI/ML infrastructure, deep expertise in LLM/VLM inference, and strong communication with researchers, engineers, and executives.

Qualifications

• 8+ years in AI/ML infrastructure, with deep expertise in LLM/VLM inference optimization and production deployment at scale.
• Deep understanding of transformer inference acceleration: quantization (INT4/FP8), speculative decoding, disaggregated inference, continuous batching, KV cache optimization, and WideEP for MoE models.
• Understanding of GPU memory hierarchies and low-latency networking along with their influence on inference performance.
• Proven track record to lead technical initiatives.
• Excellent communication skills, effective with research scientists, infrastructure engineers, and executive team members.

Responsabilités

• Lead the inference strategy for a portfolio of EMEA AI Native customers, guiding engagements from POC to production-scale deployments.
• Identify inference challenges across deployments including latency, efficiency, cost per token, memory utilization, and low-latency networking.
• Architect and optimize high-performance inference pipelines using NVIDIA Dynamo, TensorRT-LLM, vLLM, SGLang, and other backends; improve GPU utilization and cluster efficiency.
• Translate customer insights into actionable product feedback to shape the roadmap for NVIDIA stack.

Connaissances

AI/ML infrastructure

LLM/VLM inference

Transformer optimization

GPU memory management

Low-latency networking

Leadership

Formation

MS or PhD in CS/Engineering

Outils

NVIDIA Dynamo

TensorRT-LLM

vLLM

Kubernetes

Description du poste

NVIDIA is seeking a Senior Solutions Architect to lead large-scale AI inference across EMEA, collaborating with frontier labs and enterprises to deploy AI at scale. You will define technical direction, optimize inference pipelines, and drive adoption of NVIDIA technologies across customer environments.

The role requires 8+ years in AI/ML infrastructure, deep expertise in LLM/VLM inference, and strong communication with researchers, engineers, and executives.