Operations Expert Agentic Automation

My responsibilities:

• Ensuring stable and reliable operations of Agentic Automation solutions by monitoring performance, availability and incident trends across platforms and GenAI components
• Operating automation solutions according to ITSM standards and agreed SLAs, including planning and coordination of changes, releases and hotfixes
• Performing first- and second-level analysis for incidents, including configuration and workflow-level fixes within defined guardrails, and driving sustainable fixes with development teams where code changes are required
• Ensuring agent reliability and quality by maintaining and improving monitoring, logging, alerting, guardrails and runbooks, including mechanisms to detect model drift and undesired outputs
• Collaborating closely with developer teams and business functions to plan and execute deployments and optimisations as part of change management
• Documenting operational controls and maintaining a living knowledge base (runbooks, FAQs, troubleshooting guides), and providing transparency on incidents, problems and related risks to central business and IT stakeholders

The knowledge I own:

• Professional experience in IT operations, application management or platform operations, ideally with a focus on automation, integration or AI-enabled solutions
• Solid understanding of ITSM processes (incident, problem, change, request fulfilment) and experience working with common ITSM tools
• Experience in operating or supporting automation/orchestration platforms (e.g. n8n, UiPath, SAP Joule or comparable tools) or other business-critical applications
• Strong analytical and troubleshooting skills, including the ability to debug complex workflows and data flows
• Good communication skills and the ability to work collaboratively with business, development and architecture teams
• Fluent and effective communication in English within an international team
• Growth-oriented mindset with willingness to learn new platforms and technologies

• Experience with monitoring and observability for LLM or ML-based applications (dashboards, alerts, log analysis, behaviour metrics)
• Basic knowledge of automation development or scripting (e.g. Python, PowerShell) to support diagnostics and minor fixes
• Experience in working with external development/service center setups or partner teams
• Familiarity with AI governance, compliance or ethical AI guidelines in an enterprise context
• You actively use AI tools to improve your productivity and development workflow

• Opportunity to work on a large-scale platform used by thousands of users across the organization, leveraging a modern technology stack (Azure, Kubernetes, Terraform, etc.)
• Participation in building advanced analytics and automation solutions using modern cloud infrastructure and tooling
• Small, highly technical teams with strong ownership of solutions and architecture
• Strong support for professional growth through trainings, conferences and internal knowledge sharing
• Open, collaborative working culture with close interaction between engineering and business teams
• International collaboration with teams across multiple business domains
• Flexible working hours with home office possibility

Imagine a company where ALDI’s well-known quality and reliability meet IT expertise and innovation. ALDI International IT Services (AIIS) strives to achieve this every day: as part of ALDI DX, it supports a wide range of IT and business services for the ALDI SÜD Group from Hungary.

Founded in 2012 and operating as an individual business entity since 2018, AIIS has grown to nearly 1,000 employees, with offices in Budapest, Biatorbágy, Pécs and Debrecen. Its portfolio includes IT support for ALDI stores and regional headquarters across Europe and beyond – from the UK and Ireland to Germany, Austria, Italy, Switzerland, Slovenia and Hungary.

Please use our online application and attach your resume.