Remote AI Infrastructure Engineer – GPU ML Ops (EMEA)

Pragmatike; Madrid; On-site; EUR 60,000 - 80,000; Full time

Benefits offered by this job

Work from home flexibility

Inclusive recruitment process

Opportunity to influence core engineering decisions

Job summary

Pragmatike is looking for an AI Infrastructure Engineer to join a fast-growing startup in Madrid, fully remote. The role involves building production-grade model serving infrastructure for AI systems, focusing on efficient ML inference platforms. Candidates should have 4+ years of relevant experience, skills in model serving frameworks like vLLM and TGI, and a strong background in container orchestration. Join a dynamic team to drive innovations in AI-native cloud services.

Qualifications

• 4+ years of experience in ML Ops, Platform Engineering, SRE, or similar infrastructure roles focused on ML systems.
• Hands-on experience with model serving frameworks such as vLLM, TGI, Triton, or equivalent.
• Strong background in container orchestration and operating GPU-based workloads in production.

Responsibilities

• Build and operate production-grade model serving infrastructure using frameworks such as vLLM, TGI, Triton.
• Design and implement robust deployment pipelines for ML models.
• Develop and maintain auto-scaling systems and intelligent request routing layers.

Skills

ML Ops

Platform Engineering

SRE

Model serving frameworks (vLLM, TGI, Triton)

Container orchestration

Infrastructure-as-code tools (Terraform, Helm)

Python

Distributed systems

Performance tuning

Tools

Terraform

Helm

Kubeflow

MLflow

Job description

Pragmatike is looking for an AI Infrastructure Engineer to join a fast-growing startup in Madrid, fully remote. The role involves building production-grade model serving infrastructure for AI systems, focusing on efficient ML inference platforms. Candidates should have 4+ years of relevant experience, skills in model serving frameworks like vLLM and TGI, and a strong background in container orchestration. Join a dynamic team to drive innovations in AI-native cloud services.