Remote AI Infrastructure Engineer - GPU/ML Ops

Pragmatike; Turkey; On-site; TRY 2,252,252 - 4,054,054; Full time

Benefits offered by this job

Ownership of critical infrastructure

Foundation building in high-growth startup

Influence core engineering decisions

Job summary

Pragmatike is seeking an AI Infrastructure Engineer to build efficient ML inference platforms for AI applications. The role requires 4+ years of experience in ML Ops or SRE, familiarity with model serving frameworks, and a solid foundation in GPU workloads. You will design production-grade infrastructure and optimize performance, working remotely across EMEA. Join a fast-growing cloud startup influencing core engineering decisions and addressing modern challenges in infrastructure development.

Qualifications

• 4+ years in ML Ops, Platform Engineering, or similar roles.
• Hands-on experience with model serving frameworks.
• Strong container orchestration experience.

Responsibilities

• Build and operate production-grade model serving infrastructure.
• Design robust deployment pipelines for ML models.
• Optimize GPU utilization and model storage performance.
• Manage model registries and CI/CD pipelines.

Skills

Production-grade model serving

GPU-based workloads

MLOps tooling

Infrastructure as code

Python

Distributed systems

Tools

vLLM

TGI

Triton

Terraform

Helm

Job description

Pragmatike is seeking an AI Infrastructure Engineer to build efficient ML inference platforms for AI applications. The role requires 4+ years of experience in ML Ops or SRE, familiarity with model serving frameworks, and a solid foundation in GPU workloads. You will design production-grade infrastructure and optimize performance, working remotely across EMEA. Join a fast-growing cloud startup influencing core engineering decisions and addressing modern challenges in infrastructure development.