Job
- Level
- Experienced
- Job Field
- IT, Data, DevOps
- Employment Type
- Full Time
- Contract Type
- Permanent employment
- Location
- Stuttgart, Berlin
- Working Model
- Hybrid, Onsite
Job Summary
In this role, you develop AI services in the cloud, integrate LLMs and RAG applications, build monitoring and observability concepts, and optimize the operation of secure and high-performance solutions for GenAI.
Job Technologies
Your role in the team
- As a Cloud Engineer with a focus on AI services, you will drive the expansion of our cloud platform specifically for AI and GenAI applications, while ensuring that these solutions can be operated transparently, measurably, and stably.
- You utilize the existing LBBW cloud infrastructure to provide powerful services for LLMs, RAG, Agentic AI, and MCP servers, optimally integrating them into our IT landscape and securing them with monitoring, logging, and tracing solutions.
- In your role, you combine cloud, platform, and automation expertise with the specific requirements of modern AI workloads: you design operational, security, scaling, cost, and observability concepts, define metrics and dashboards, and work closely with GenAI, architecture, and development teams to ensure that AI solutions can be operated safely, efficiently, and transparently at LBBW.
- Design, implementation, and operation of AI and LLM platform components (e.g., Azure OpenAI, proprietary LLM deployments, vector databases, retrieval/RAG services) as well as integration of internal systems (REST APIs, databases, specialized applications).
- Development of the technical foundation for LLM endpoints, tool/function calling, orchestration, and MCP server, as well as integration into existing system landscapes and Agentic AI scenarios.
- Integration of relevant data sources (e.g., databases, DWH, data lake, document repositories) including role and permission concepts, as well as collaboration on security and guardrail concepts (ID and API management, content filtering, data leakage prevention).
- Implementation and maintenance of Infrastructure as Code (e.g., Terraform, Bicep) as well as integration of platform and observability components into CI/CD pipelines (Azure DevOps, GitHub Actions) based on defined platform standards, reference architectures, and landing zones.
- Development and enhancement of observability concepts for AI services (latency, error rates, resources, costs, usage patterns) including the implementation of monitoring, logging, and tracing solutions (e.g., Azure Monitor, Application Insights, dashboards, alerts, SLIs/SLOs) as well as collaboration on auto-scaling, limits, quotas, and cost alerting concepts.
- Participation in incident and problem management (root cause analysis, improvement measures), creation of runbooks, playbooks, best practices, and architecture documents related to scaling, observability, security, and cost, as well as consulting projects for the optimal use of the AI platform.
This text has been machine translated. Show original
Our expectations of you
Education
- Completed degree in (Business) Informatics or a comparable qualification.
Qualifications
- Practical experience with Infrastructure as Code, CI/CD, and cloud workload operations.
- Understanding of security, governance, and network architectures in cloud environments.
- Structured, quality-conscious, and self-responsible way of working.
- Team-oriented and communicative, confident in interactions with development, architecture, security, operations, and business units.
- Pragmatic and resilient, with a passion for providing a robust and transparent platform for many teams.
- Very good spoken and written German skills.
Experience
- Experience in cloud and infrastructure environments, ideally with large, production environments.
- Experience with monitoring, logging, and tracing solutions (e.g., Azure Monitor, Application Insights).
This text has been machine translated. Show original
What we offer
- Modern talent management for career development.
- Active promotion of a good work-life balance (including flexible working hours, sabbaticals, and the possibility to work partially remotely or from home).
- Attractive company pension scheme.
- Comprehensive health management (including partnerships with fitness studios, occupational health services, preventive examinations).
- Interesting leasing options, e.g., company bike, tablet, smartphone.
- Great lunch offers (organic, vegetarian, or vegan).
This text has been machine translated. Show original
Benefits
Health, Fitness & Fun
Work-Life-Integration
Topics that you deal with on the job
Job Locations
This is your employer
Landesbank Baden-Württemberg
Sie möchten Ihre Fähigkeiten und Kompetenzen in einer der größten Banken Deutschlands zielgerichtet weiterentwickeln? Dann sind Sie bei der LBBW genau an der richtigen Stelle. Leistungsfähige und engagierte Mitarbeiterinnen und Mitarbeiter sind unser zentraler Erfolgsfaktor. Mit Eigeninitiative und Verantwortungsbewusstsein schaffen wir nachhaltig Wert für unsere
Description
- Company Type
- Established Company
- Working Model
- Hybrid, Onsite
- Industry
- Banking, Finance, Insurance
Cloud Engineer with a focus on AI Services
- Location
- Stuttgart, Berlin
- Working Model
- Hybrid, Onsite
- Diversity
- Open for all genders
