MLOps Engineer

Koda Tech; Antwerpen; On-site; EUR 75,000 - 110,000; Full time

Job summary

Koda Tech is Antwerp-based and is building a new enterprise AI platform to securely enable employees and engineering teams to develop, deploy and use AI solutions using internal data. We seek an MLOps / AI Platform Engineer with 3+ years of experience across MLOps, DevOps, platform engineering or AI infrastructure to help design, deploy and operate the infrastructure that supports the platform.

You will work at the intersection of AI engineering, MLOps and infrastructure, contributing to

Qualifications

• Minimum 3 years of professional experience within MLOps, DevOps, Platform Engineering, Cloud/Infrastructure Engineering or a closely related position.
• Experience working with ML or LLM workloads, including model serving, vector databases, GPU workloads, AI/ML infrastructure.
• Strong knowledge of Kubernetes and/or OpenShift.
• Experience with observability technologies such as Prometheus, Grafana, Elastic or similar tooling.
• Understanding of container security, including network policies, workload isolation and pod security.
• Scripting and automation experience using Python or Go.

Responsibilities

• Configure and manage OpenShift environments, including namespaces, network policies and resource allocation.
• Build and maintain monitoring, observability and alerting across the AI platform.
• Work with Elastic, Prometheus, Grafana and LangSmith to support workloads.
• Establish visibility across LLM workloads, prompts, token usage, latency and evaluation.
• Integrate platform logging with centralized logging and SIEM environments.
• Help design and prepare GPU infrastructure for on-premise model inference.
• Support GPU scheduling, capacity planning and infrastructure requirements as AI usage grows.
• Build secure and isolated environments for executing AI workloads.
• Take ownership of operational readiness, including backup and recovery procedures, runbooks and on-call processes.
• Automate infrastructure and operational processes using Python or Go.
• Collaborate with AI engineers, platform engineers and wider infrastructure teams.

Skills

MLOps

DevOps

Platform Engineering

Kubernetes/OpenShift

Python/Go scripting

Education

Bachelor's or Master's degree in Computer Science or related

Tools

OpenShift

Kubernetes

Prometheus

Grafana

Elastic

LangSmith

SIEM

Job description

I’m working with an established organisation in Antwerp that is investing heavily in its internal AI capabilities and building a new enterprise AI platform.

The platform will give employees and engineering teams a secure environment to build, deploy, and use AI solutions based on internal company knowledge and data.

As their AI engineering function continues to grow, they are looking for an MLOps / AI Platform Engineer with at least 3 years’ professional experience across MLOps, DevOps, Platform Engineering, or AI infrastructure.

The Role

You’ll work at the intersection of AI engineering, MLOps and infrastructure, helping build and operate the infrastructure layer supporting the wider AI platform.

The environment combines OpenShift, Kubernetes, LLM workloads, observability, security and on-premise infrastructure.

You’ll be involved in everything from container environments and monitoring through to secure AI workloads and the infrastructure required to run models internally.

Key Responsibilities

• Configure and manage OpenShift environments, including namespaces, network policies and resource allocation.
• Build and maintain monitoring, observability and alerting across the AI platform.
• Work with technologies including Elastic, Prometheus, Grafana and LangSmith.
• Establish visibility across LLM workloads, including prompts, token usage, latency and evaluation.
• Integrate platform logging with centralised logging and SIEM environments.
• Help design and prepare GPU infrastructure for on-premise model inference.
• Support GPU scheduling, capacity planning and infrastructure requirements as AI usage grows.
• Build secure and isolated environments for executing AI workloads.
• Take ownership of operational readiness, including backup and recovery procedures, runbooks and on-call processes.
• Automate infrastructure and operational processes using Python or Go.
• Collaborate with AI engineers, platform engineers and wider infrastructure teams.

What They’re Looking For

• Minimum 3 years of professional experience within MLOps, DevOps, Platform Engineering, Cloud/Infrastructure Engineering or a closely related position.
• Experience working with ML or LLM workloads, ideally involving areas such as:
• Model serving
• Vector databases
• GPU workloads
• AI/ML infrastructure
• Strong knowledge of Kubernetes and/or OpenShift.
• Experience with observability technologies such as Prometheus, Grafana, Elastic or similar tooling.
• Understanding of container security, including:
• Network policies
• Workload isolation
• Pod security
• Scripting and automation experience using Python or Go.
• Bachelor's or Master's degree in Computer Science or a related technical discipline.
• Fluent English.
• Dutch is a strong advantage, while French is beneficial.

Why Consider It?

This is an opportunity to join an AI platform initiative at an early stage, rather than simply stepping into an established maintenance environment.

You’ll have the opportunity to work across MLOps, Kubernetes/OpenShift, LLM infrastructure, observability, platform security and GPU computing, helping build the technical foundations required to move AI applications securely into production.

The position offers a permanent contract, competitive salary and benefits package, alongside long-term career development opportunities within an established organisation.