4 days ago
Garching bei München, GermanySenior / Staff+
Responsibilities
- Define production-readiness requirements and the handover framework for FDE engagements transitioning from Value Delivery to Value Operation.
- Build monitoring, alerting, incident response, and SLA-management capabilities for deployed AI solutions.
- Establish AI production-quality practices including drift detection, performance benchmarking, guardrail validation, and retraining triggers.
- Define operational governance for production security, data boundaries, compliance, and self-healing capabilities.
- Design scalable tooling, automation, and partner-integration models for multiple customer engagements.
- Capture operational learnings with the Knowledge & IP team and feed them into the delivery lifecycle.
- Mentor engineers, set operational standards, and collaborate with delivery squads, platform teams, customers, and external partners.
Requirements
- Hands-on experience operating LLM-based systems, agentic workflows, and distributed architectures in customer production environments.
- Deep experience with observability, incident management, and production reliability across cloud environments.
- Experience identifying behavioral drift in agentic applications and managing production quality.
- Experience in regulated or enterprise-grade environments with compliance, security posture, data boundaries, and operational governance requirements.
- Ability to create standards, playbooks, repeatable processes, scalable operational models, and self-healing capabilities.
- Experience collaborating across engineering teams, customers, external partners, and architectural stakeholders.
- Skills associated with the role include agentic AI practice, AI output quality assurance, context engineering, agentic orchestration, agentic engineering, application security, cloud architecture, and evaluations and benchmarking engineering.
Benefits
- Learning and development opportunities.
- Flexible working models.
- Health and well-being support.
- Global collaboration across FDE squads and hubs.
Categories
Site Reliability
About SAP
SAP builds enterprise application software and cloud services for finance, procurement, supply chain, human resources, and analytics, sold through subscriptions, licenses, and support. Its portfolio includes SAP S/4HANA, SAP Business Technology Platform, SAP Ariba, and SAP SuccessFactors. Founded in 1972 and headquartered in Walldorf, Germany, SAP is a public company listed on the NYSE and Frankfurt (ETR) and serves enterprises and public-sector organizations worldwide.