Senior AI Inference Architect for Large-Scale Deployments

Talanto; France; Hybride; EUR 68 000 - 150 000; Plein temps

Résumé du poste

Talanto is seeking a Senior Solutions Architect to lead AI inference strategy across EMEA. You will guide engagements from proof of concept to production-scale deployments, architect high-performance inference pipelines, and optimize GPU utilization for large-scale AI workloads.

The role requires deep expertise in LLM/VLM inference, transformer acceleration, and Kubernetes-based orchestration. Join a frontier AI environment with strong collaboration across research and enterprise teams.

Qualifications

• MS or PhD in CS, Engineering, or equivalent.
• 8+ years in AI/ML infrastructure and production deployment at scale.
• Deep expertise in transformer inference acceleration: quantization, speculative decoding, and KV cache optimization.
• Understanding GPU memory hierarchies and low-latency networking for inference.
• Proven track record leading technical initiatives.
• Excellent communication with researchers, engineers, and executives.

Responsabilités

• Define the technical direction for AI inference across EMEA.
• Lead inference strategy from PoC to production deployments.
• Architect and optimize high-performance inference pipelines using listed backends.
• Translate customer insights into actionable feedback shaping stack roadmaps.

Connaissances

AI/ML infrastructure

Leadership

Technical collaboration

Transformer inference

Formation

MS/PhD in CS or Engineering

Outils

Dynamo

TensorRT-LLM

vLLM

SGLang

Kubernetes

NIM

Description du poste

Talanto is seeking a Senior Solutions Architect to lead AI inference strategy across EMEA. You will guide engagements from proof of concept to production-scale deployments, architect high-performance inference pipelines, and optimize GPU utilization for large-scale AI workloads.

The role requires deep expertise in LLM/VLM inference, transformer acceleration, and Kubernetes-based orchestration. Join a frontier AI environment with strong collaboration across research and enterprise teams.