Senior AI Inference Architect for Multi-Node GPU Scale

NVIDIA Corporation; France; Hybride; EUR 120 000 - 180 000; Plein temps

Résumé du poste

NVIDIA Corporation in France is seeking a Senior Solutions Architect with deep expertise in large-scale production AI inference. You will guide EMEA customers, design efficient inference pipelines, and collaborate with NVIDIA product teams to accelerate success across multi-node GPU clusters.

The role requires a MS/PhD in a related field or equivalent experience, 5+ years in neural network inference optimization, and proven ability to engage ML engineers, researchers, and architects.

Qualifications

• MS or PhD in Computer Science, Engineering, High-Performance Computing, or equivalent professional experience.
• 5+ years of neural networks inference optimization experience.
• Strong knowledge of transformers inference optimization: quantization, disaggregated inference, speculative decoding, continuous batching, KV cache optimization.
• Experience with MoE inference at scale: expert parallelism, WideEP, all-to-all communication, routing overhead, and load balancing at scale.
• Ability to engage effectively with ML engineers, researchers, and systems architects at a deep technical level.

Responsabilités

• Guide EMEA AI Natives customers in deploying and optimizing large-scale inference workloads on multi-node GPU clusters.
• Architect efficient inference pipelines for dense and sparse/latent MoE models distributing workload among thousands of GPUs.
• Improve inference efficiency across quantization (INT4/FP8), speculative decoding, disaggregated prefill/decode, KV cache management, and WideEP for large MoE deployments.
• Collaborate with NVIDIA product teams (Dynamo, TensorRT-LLM, NIXL) to accelerate customer success.
• Animate the AI inference developer’s community across EMEA through technical workshops, hackathons, and reference architectures.

Connaissances

Neural networks inference optimization

MoE inference at scale

Multi-node GPU clusters

Quantization optimization

KV cache optimization

Formation

MS or PhD in Computer Science/Engineering/HPC

Outils

Dynamo

NIXL

Grove

TensorRT-LLM

UCX

Description du poste

NVIDIA Corporation in France is seeking a Senior Solutions Architect with deep expertise in large-scale production AI inference. You will guide EMEA customers, design efficient inference pipelines, and collaborate with NVIDIA product teams to accelerate success across multi-node GPU clusters.

The role requires a MS/PhD in a related field or equivalent experience, 5+ years in neural network inference optimization, and proven ability to engage ML engineers, researchers, and architects.