Senior AI Inference Architect: Scale Deployments EMEA

NVIDIA; Marseille; Vor Ort; EUR 120.000 - 190.000; Vollzeit

Benefits dieser Stelle

Competitive salary

Benefits package

Zusammenfassung

NVIDIA is seeking a Senior Solutions Architect to lead technical collaborations across the EMEA region, defining the direction for AI inference at scale for frontier labs and enterprises. You will drive scalable, high-impact solutions by aligning NVIDIA teams with customer needs and shaping deployment patterns.

You will architect and optimize inference pipelines using Dynamo, TensorRT-LLM, vLLM, SGLang, and other backends, translating insights into a roadmap for NVIDIA’s stack and ensuring

Qualifikationen

• MS or PhD in Computer Science, Engineering, or equivalent experience.
• 8+ years in AI/ML infrastructure with production deployment at scale.
• Deep understanding of transformer inference acceleration and GPU memory hierarchies.

Aufgaben

• Lead the inference strategy for a portfolio of EMEA AI Natives customers from PoC to production scale.
• Identify latency, efficiency, cost per token, memory utilization, and low-latency networking challenges.
• Architect and optimize high-performance inference pipelines using Dynamo, TensorRT-LLM, vLLM, SGLang, and other backends.
• Translate deployment patterns into actionable product feedback and a roadmap for NVIDIA stack.

Kenntnisse

LLM inference

VLM inference

Inference optimization

GPU utilization

Communication with researchers

Leadership

Ausbildung

MS/PhD in CS/Engineering

Tools

NVIDIA Dynamo

TensorRT-LLM

vLLM

Kubernetes

NIM

Jobbeschreibung

NVIDIA is seeking a Senior Solutions Architect to lead technical collaborations across the EMEA region, defining the direction for AI inference at scale for frontier labs and enterprises. You will drive scalable, high-impact solutions by aligning NVIDIA teams with customer needs and shaping deployment patterns.

You will architect and optimize inference pipelines using Dynamo, TensorRT-LLM, vLLM, SGLang, and other backends, translating insights into a roadmap for NVIDIA’s stack and ensuring