Senior ML Ops Engineer - Remote GPU Inference

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

Job summary

Pragmatike is recruiting for an ML Ops Engineer to design, build and operate scalable inference platforms powering AI workloads in a remote-first setup across the EMEA region. You will collaborate with infrastructure, platform, and applied AI teams to ensure low latency and cost-efficient deployments.

The role emphasizes production-grade model serving, distributed GPU systems, and ownership of the full ML lifecycle from development to production in a fast-growing startup context.

Qualifications

• 4+ years of experience in ML Ops, Platform Engineering, SRE, or similar roles.
• Hands-on experience with model serving frameworks such as vLLM, TGI, Triton, or equivalents.
• Strong background in container orchestration and GPU-based production workloads.
• Experience with MLOps tooling including model registries, experiment tracking, and automated deployment pipelines.
• Proficiency in Python and infrastructure-as-code tools (Terraform, Helm, or similar).
• Strong understanding of distributed systems, performance tuning, and reliability engineering.
• Ownership mindset with ability to work autonomously in a remote-first environment.

Responsibilities

• Build and operate production-grade ML inference platforms powering real-time AI applications.
• Design and implement robust deployment pipelines with blue/green and canary rollout strategies for ML models.
• Develop and maintain auto-scaling systems and intelligent request routing layers.
• Optimize GPU utilization, memory efficiency, and model artifact storage performance.
• Define observability systems for tracking latency, throughput, GPU usage, cost metrics, and system health.
• Manage model registries and CI/CD pipelines enabling automated deployments.
• Own the full lifecycle of ML systems from development through production, including on-call responsibilities.
• Define engineering best practices and contribute to platform scalability in a fast-moving startup environment.

Skills

ML Ops

Model serving

Container orchestration

Python

Infrastructure as code

Distributed systems

Remote work

Tools

Terraform

Helm

Job description

Pragmatike is recruiting for an ML Ops Engineer to design, build and operate scalable inference platforms powering AI workloads in a remote-first setup across the EMEA region. You will collaborate with infrastructure, platform, and applied AI teams to ensure low latency and cost-efficient deployments.

The role emphasizes production-grade model serving, distributed GPU systems, and ownership of the full ML lifecycle from development to production in a fast-growing startup context.