Lead ML Ops Engineer - Remote GPU Inference Platform

Pragmatike; Lisboa; On-site; EUR 90,000 - 130,000; Full time

Job summary

Pragmatike is recruiting an ML Ops Engineer to build scalable, reliable ML inference platforms for real-time AI workloads. You will design and operate core infrastructure serving machine learning models at scale, collaborating with infra, platform, and applied AI teams for high availability and low latency.

This remote-first role requires deep ownership and experience with distributed GPU systems, enabling cost-efficient AI deployments in a fast-growing startup.

Qualifications

• 4+ years in ML Ops or platform engineering focused on ML systems.
• Hands-on with model serving frameworks (vLLM, TGI, Triton or equivalent).
• Container orchestration and GPU-based production workloads.
• Experience with model registries, experiment tracking, automated deployments.
• Proficient in Python and IaC tools (Terraform, Helm).
• Strong distributed-systems knowledge and reliability engineering.
• Ability to work independently in a remote-first environment.
• Willingness to adopt AI coding assistants to accelerate work.

Responsibilities

• Build and operate production-grade model serving infrastructure.
• Design robust deployment pipelines with blue/green and canary strategies.
• Develop auto-scaling and multi-model serving architectures.
• Optimize GPU utilization, memory, network, and storage performance.
• Design observability for latency, throughput, GPU usage, and costs.
• Manage model registries and CI/CD for automated deployments.
• Own full lifecycle of ML systems from development to on-call support.
• Define engineering best practices for scalable platform growth.

Skills

ML Ops

Model serving

Container orchestration

MLOps tooling

Python

Infrastructure as code

Distributed systems

Ownership mindset

Tools

Kubeflow

MLflow

KubeAI

Job description

Pragmatike is recruiting an ML Ops Engineer to build scalable, reliable ML inference platforms for real-time AI workloads. You will design and operate core infrastructure serving machine learning models at scale, collaborating with infra, platform, and applied AI teams for high availability and low latency.

This remote-first role requires deep ownership and experience with distributed GPU systems, enabling cost-efficient AI deployments in a fast-growing startup.