Senior AI Inference Architect — Multi-Node GPU Scale

NVIDIA; Lavamünd; Vor Ort; EUR 110.000 - 170.000; Vollzeit

Zusammenfassung

NVIDIA in Austria is seeking a Senior Solutions Architect to lead production AI inference projects across EMEA. You will drive multi-node GPU deployments, optimize end-to-end latency, and shape the technical direction for scalable AI inference in demanding environments.

You will collaborate with ML engineers, researchers and system architects, own the performance roadmap, and mentor teams through workshops and reference architectures.

Qualifikationen

• MS/PhD in CS/Engineering/HPC or equivalent experience.
• 5+ years in neural networks inference optimization.
• Strong knowledge of transformers inference optimization.
• Hands-on MoE inference at scale experience.
• Ability to engage with ML engineers, researchers, and architects.

Aufgaben

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

Kenntnisse

NN inference

Transformers optimization

MoE at scale

Engagement with ML teams

Ausbildung

MS or PhD in CS/Engineering/HPC

Jobbeschreibung

NVIDIA in Austria is seeking a Senior Solutions Architect to lead production AI inference projects across EMEA. You will drive multi-node GPU deployments, optimize end-to-end latency, and shape the technical direction for scalable AI inference in demanding environments.

You will collaborate with ML engineers, researchers and system architects, own the performance roadmap, and mentor teams through workshops and reference architectures.