Senior ML Ops Engineer — Remote GPU Inference & Scale

Pragmatike; Poland; On-site; PLN 301,000 - 474,000; Full time

Job summary

Pragmatike is seeking an ML Ops Engineer to build and operate scalable ML inference platforms for AI-native cloud services. This fully remote role focuses on production-grade model serving and infrastructure for AI systems.

You will collaborate with infrastructure, platform, and applied AI teams to ensure high availability, low latency, and cost-efficient inference. Strong Python, container orchestration, and MLOps tooling are essential for success.

Qualifications

• 4+ years of experience in ML Ops or similar infrastructure roles focused on ML systems.

Responsibilities

• Build production‑grade model serving infrastructure using ML frameworks (vLLM, TGI, Triton).
• Design deployment pipelines with blue/green and canary strategies for ML models.
• Develop and maintain auto-scaling and multi‑model serving architectures.
• Optimize GPU utilization, memory, network and storage performance.
• Design observability for latency, throughput, GPU usage and cost metrics.
• Manage model registries and CI/CD for automated deployments.
• Own end-to-end lifecycle of ML systems with on‑call responsibilities.
• Define best practices and contribute to scalable platform decisions.

Skills

ML Ops

Platform Eng

Python

Terraform/Helm

GPU clusters

Container orchestration

Tools

vLLM

TGI

Triton

Kubernetes

Docker

Terraform

Helm

Job description

Pragmatike is seeking an ML Ops Engineer to build and operate scalable ML inference platforms for AI-native cloud services. This fully remote role focuses on production-grade model serving and infrastructure for AI systems.

You will collaborate with infrastructure, platform, and applied AI teams to ensure high availability, low latency, and cost-efficient inference. Strong Python, container orchestration, and MLOps tooling are essential for success.