Senior AI Inference Architect: Multi-Node GPU Scale

NVIDIA; Marseille; Sur place; EUR 120 000 - 180 000; Plein temps

Résumé du poste

NVIDIA is seeking a Senior Solutions Architect to lead large-scale AI inference deployments in production. You will guide EMEA customers, optimize multi-node GPU clusters, and collaborate with product teams to accelerate success across the inference stack.

You will shape the technical direction for high-performance AI workloads, addressing MoE inference, memory-bound workloads, and interconnect-aware scheduling in demanding environments in France and beyond.

Qualifications

• MS or PhD in CS, Engineering, HPC or equivalent.
• 5+ years in neural networks inference optimization.
• Deep knowledge of transformers inference optimization.
• Experience with MoE inference at scale.
• Ability to engage with ML engineers, researchers, and systems architects.

Responsabilités

• Guide EMEA customers in deploying large-scale inference workloads on multi-node GPU clusters.
• Architect efficient inference pipelines for dense and MoE models across thousands of GPUs.
• Improve inference efficiency across quantization, speculative decoding, and KV cache management.
• Collaborate with product teams to accelerate customer success.
• Lead technical workshops and reference architectures across EMEA.

Connaissances

Neural inference optimization

Transformers optimization

MoE inference at scale

Technical leadership

Client engagement

Formation

MS or PhD in CS/Engineering/HPC

Description du poste

NVIDIA is seeking a Senior Solutions Architect to lead large-scale AI inference deployments in production. You will guide EMEA customers, optimize multi-node GPU clusters, and collaborate with product teams to accelerate success across the inference stack.

You will shape the technical direction for high-performance AI workloads, addressing MoE inference, memory-bound workloads, and interconnect-aware scheduling in demanding environments in France and beyond.