Senior AI Inference Architect – Large-Scale Neural Nets

NVIDIA; Poland; On-site; PLN 375,000 - 650,000; Full time

Job summary

NVIDIA seeks a Senior Solutions Architect with deep expertise in large-scale neural network inference to lead collaboration with frontier AI labs and enterprises deploying AI at scale across EMEA. You will define the technical direction for AI inference, identify bottlenecks, and drive scalable, high-impact solutions.

By aligning key NVIDIA and customer teams, you will influence strategic decisions and guide deployment across Poland and beyond, shaping the next generation of inference stack,

Qualifications

• MS or PhD in Computer Science, Engineering, or equivalent.
• 8+ years in AI/ML infrastructure with production deployments.
• Deep understanding of transformer inference acceleration.
• Knowledge of GPU memory hierarchies and low-latency networking.
• Proven ability to lead technical initiatives.
• Excellent communication with researchers, engineers, and executives.

Responsibilities

• Lead the inference strategy for an EMEA customer portfolio from POC to production-scale deployments.
• Identify latency, efficiency, cost per token, and memory bottlenecks in deployments.
• Architect and optimize high-performance inference pipelines using Dynamo, TensorRT-LLM, vLLM, and more.
• Translate insights into product feedback for roadmap of NVIDIA stack.

Skills

MS/PhD in CS/Engineering

8+ years AI/ML infra

Transformer inference acceleration

GPU memory hierarchies & low-latency

lead technical initiatives

strong cross-group communication

Education

MS or PhD in Computer Science, Engineering, or equivalent

Tools

TensorRT-LLM

NVIDIA Dynamo

Kubernetes

Job description

NVIDIA seeks a Senior Solutions Architect with deep expertise in large-scale neural network inference to lead collaboration with frontier AI labs and enterprises deploying AI at scale across EMEA. You will define the technical direction for AI inference, identify bottlenecks, and drive scalable, high-impact solutions.

By aligning key NVIDIA and customer teams, you will influence strategic decisions and guide deployment across Poland and beyond, shaping the next generation of inference stack,