- Location
- Cologne, Nordrhein-Westfalen, Germany
- Workplace
- Hybrid
- Type
- Full-time
- Department
- KI performance
- Seniority
- Senior
- Source
- Recruitee
Description
🚀 Become our new MLOps Engineer (all genders)
At KI Performance, we move AI from experimentation to production. As a MLOps Engineer, you will design, build, and operate highly scalable, secure Azure-based AI platforms used in production environments. This role sits at the intersection of cloud infrastructure, DevOps, and AI delivery, with a strong focus on enabling iterative AI development, reliable model deployment, and platform scalability.
You will work closely with AI engineers, data teams, and product stakeholders to ensure that AI use cases can be developed, deployed, and operated efficiently at scale — with production-grade reliability, security, and observability.
Your responsibilities
Cloud Infrastructure & Platform Engineering
Design, implement, and operate scalable Azure infrastructure for AI and data-intensive platforms using Terraform
Build and maintain secure Azure networking architectures (VNETs, subnets, NSGs, Private Endpoints)
Implement access control and governance using Azure RBAC, Key Vault, and Azure Policies
Ensure infrastructure is production-ready with a focus on performance, reliability, and scalability
CI/CD & Release Engineering
Design and operate modern CI/CD pipelines using GitHub Actions
Enable fast, safe, and repeatable deployments for infrastructure, services, and AI models
Support iterative development with strong versioning, testing, and rollback strategies
MLOps & AI Platform Enablement
Operationalize AI use cases using MLflow (experiment tracking, model registry, deployment workflows)
Support the full AI lifecycle from experimentation to production deployment
Deploy and operate model inference services exposed via REST APIs (FastAPI preferred)
Collaborate closely with AI engineers to ensure models are production-ready
Observability & Reliability
Implement end-to-end observability using OpenTelemetry
Set up monitoring and logging using Azure Application Insights (or equivalent tooling)
Proactively improve system reliability, performance, and incident response
Engineering & Automation
Use Python for automation, AI integration, backend services, and tooling
Support platform self-service capabilities for engineering teams
Continuously improve infrastructure and operational maturity