Latest AI JobsBrowse Jobs
pragmatike logo

ML Ops Engineer (EMEA Remote)

pragmatikeUkraineWork with our Clients
Apply on company site
Salary
Not listed
Job type
Full-time
Work mode
Remote
Experience
Senior · 4+ yrs
Posted
23 Sept 2026
Status
Open · checked 9d ago

About this role

The ML Ops Engineer (EMEA Remote) role is a fully remote position based in the EMEA timezone, hired through Pragmatike for a distributed cloud infrastructure startup. This technical position suits professionals with a strong background in production-grade model serving and infrastructure who want to build scalable machine learning inference platforms.

Role Overview

Pragmatike is recruiting an ML Ops Engineer for a well-funded, fast-scaling cloud infrastructure startup building AI-native cloud services. The organization provides GPU-powered infrastructure, secure storage, and high-speed data transfer through a decentralized architecture. This hands-on position focuses on creating reliable, scalable, and efficient inference systems to power real-time artificial intelligence applications while collaborating with platform, infrastructure, and applied AI teams.

Key Responsibilities

Construct and manage production-grade model serving infrastructure using tools like Triton, TGI, vLLM, or equivalent frameworks.
Create and execute deployment pipelines featuring blue/green and canary rollout methodologies for machine learning models.
Maintain and build auto-scaling systems, multi-model serving setups, and intelligent request routing layers.
Enhance GPU performance, memory usage, network throughput, and storage efficiency for model artifacts.
Establish observability platforms to monitor system health, inference latency, throughput, cost metrics, and GPU utilization.
Oversee model registries and CI/CD pipelines to support automated and reproducible deployments.
Handle the complete lifecycle of machine learning systems, including operational support and on-call duties.
Establish engineering standards and aid platform scalability within a growing startup setting.

Requirements

Four or more years of professional experience in MLOps, Site Reliability Engineering, Platform Engineering, or related infrastructure roles centered on machine learning systems.
Practical background using model serving technologies such as Triton, TGI, vLLM, or similar alternatives.
Solid experience in container orchestration and running GPU workloads in production environments.
Familiarity with MLOps tools encompassing automated deployment pipelines, model registries, and experiment tracking.
Competence in Python along with infrastructure-as-code technologies like Terraform or Helm.
Comprehensive knowledge of distributed systems, production reliability engineering, and performance tuning.
Capability to utilize AI coding assistants to improve debugging and development workflows.
Independent working style suited to a remote-first company structure.

Nice to Have

Background with machine learning platforms including MLflow, Kubeflow, or KubeAI.
Familiarity with multi-tenant inference systems, CUDA or ROCm optimization, and GPU scheduling.
Experience optimizing costs across various inference workloads and GPU types.
History of working in early-stage startups or greenfield infrastructure projects.
Demonstrated ability to construct production systems from the ground up rather than supporting legacy platforms.

Skills and Tools

Python
Terraform
Helm
vLLM
TGI
Triton
MLflow
Kubeflow
KubeAI
CUDA
ROCm

About the Company

Pragmatike acts as a recruitment partner for a well-funded, fast-scaling distributed cloud infrastructure startup focused on sustainable AI-native cloud services. The company emphasizes decentralized architecture to reduce environmental impact while delivering GPU-powered infrastructure for artificial intelligence workloads. Pragmatike adheres to a transparent, fair, and inclusive recruitment policy compliant with GDPR regulations.

How to Apply

Interested candidates should apply on the official company careers page.

Skills and tech stack

PythonTerraformHelmvLLMTGITritonMLflowKubeflowKubeAICUDAROCmMLOpsMachine LearningDistributed Systems

Questions candidates ask

Where is the ML Ops Engineer position located?

The position is fully remote within the EMEA timezone.

How many years of experience are required for this role?

Candidates must have four or more years of experience in MLOps, Site Reliability Engineering, Platform Engineering, or related infrastructure roles focused on machine learning systems.

What programming language and infrastructure tools are needed?

Proficiency in Python and infrastructure-as-code tools such as Terraform or Helm is required.

What model serving frameworks are mentioned in the requirements?

Required tools include model serving frameworks like vLLM, TGI, Triton, or equivalent technologies.

Is visa sponsorship available?

Visa sponsorship is not mentioned in the posting.

Ready to apply?

The application is on the official pragmatike careers page.

Apply on company site