DevOps / KI-Ops Engineer (m/w/d), Bank11
Core
Designing and operating production infrastructure for AI systems, including model serving, orchestration, and scaling.
Role type
DevOps / KI-Ops Engineer
Builds
Stable, performant, and secure deployment and infrastructure processes for AI workloads.
Domain
Banking / AI Infrastructure
Deliverable
production ML models
Required skills
AI system administration, Continuous Delivery (GitLab), MCP Server deployment, IT Security, Configuration API, Service Management, Container technologies, Cloud technologies, GPU planning, Model versioning, Patch management, Monitoring, Logging, Alerting, Capacity planning, Disaster recovery design, Redundancy design, Failover design.
Preferred skills
Experience with on-premise/private cloud environments, Knowledge of DORA-Resilience and ICT-Risk frameworks.
Technologies
GitLab, MCP (Model Context Protocol), Cloud/Hyperscaler, GPU, Private Cloud, On-Premise.
Responsibilities
Responsible for the production operation of the company's AI infrastructure from technical architecture to daily operations; Design technical solutions for AI infrastructure including model serving, orchestration, and scaling concepts; Implement access control and monitoring for MCP services as an integration layer between AI systems and internal/external tools; Design fault tolerance, failover, and disaster recovery concepts for AI workloads; Distribute load between cloud/hyperscaler and locally hosted models; Plan and operate local AI models (On-Premise/Private Cloud) including hardware/GPU planning, model versioning, and patch management; Develop a bank-wide reference architecture for AI infrastructure as a template for new use cases; Monitor, log, alert, and plan capacity for all production AI services; Accept release gates from the AI engineering team and ensure a stable transition to operations; Ensure regulatory requirements (DORA-Resilience, ICT-Risk framework) for AI workloads.
Seniority
Mid-level, hands-on IC