Junior AI Engineer

We are developing an agentic AI platform for Cloud Operations: autonomous agents that classify alerts, run operational playbooks, investigate incidents, and progressively refine their own skill library. The platform is organised into two layers — a control plane covering agent registration, skill governance, and human-in-the-loop orchestration, and the agents themselves, which execute on SAP BTP / Kyma. 

This position lives at the boundary between AI engineering and platform engineering. We are hiring someone who ships agents that operate reliably in production — not proofs of concept. 

What You'll Build 

• Designing and delivering LLM-driven agents based on skill-routing patterns (LangGraph, Claude API / Anthropic SDK, or comparable stacks) 

• Curating and evolving skill library — self-contained skill definitions with clearly declared tool bindings, trust levels, and confirmation checkpoints 

• Wiring agents into the systems already in production use: ServiceNow, alerting pipelines, Kyma / BTP APIs, and our internal knowledge sources 

• Contributing to shared agent memory and the feedback loops that lift skill quality over time 

• Packaging, deploying, and operating agents on SAP BTP / Kyma 

• Performing Agent testing and ensure Agents are production-ready, including authorizing tests that assess decision quality, not merely whether a task ran to completion 

Results and Outcomes  

• Delivers agents and skills within an established architecture autonomously 

• Performs comprehensive testing on agents they build 

• Effectively works in accordance with established compliance, security and governance requirements  

• Understands ITSM and ITIL practices in the context of Cloud Operations and has them in mind to ensure Agent RoI, performance and relevance 

Mindset 

• You focus on efficiency, value add and customer-centric experience  

• You actively communicate and collaborate with AI CoE and relevant teams to ensure compliance and effectiveness of AI Agents developed 

• You document your work — agent designs, skill contracts, and the reasoning behind decisions 

• You reason in terms of boundaries and contracts: what an agent is authorized to do unattended, what it must propose for approval, and what it must never do 

• You embed input from Operation team testing in Agent workflows prior implementation 

• You continuously work to develop a skill definition and initiate data-driven improvements over time 

What You Bring

Essential 

• Strong command of Python (primary language for agent work), with working fluency in TypeScript / Node 

• Practical experience building LLM applications that go well beyond prompt crafting — including tool invocation, structured output handling, and agent control loops 

• A clear grasp of agentic design patterns: skill routing, human-in-the-loop workflows, and state-machine-driven execution 

• Working familiarity with at least one agent framework — LangGraph, LangChain, AutoGen, CrewAI, or an equivalent 

• Comfort with containers and foundational Kubernetes concepts, since agents run on SAP BTP / Kyma 

• A sharp production-safety focus: recognizing the failure modes that matter — hallucination, tool misuse, runaway loops, breaches of trust boundaries 

Strongly Preferred 

• Hands-on exposure to SAP BTP, the CAP framework, or enterprise integration patterns. 

• Familiarity with ITSM and ITIL concepts — ServiceNow, the incident lifecycle, SLA management — since this is the domain in which the agents operate 

• Experience designing how AI systems are evaluated and measured  

• Hands-on experience in Cloud Operations or SRE, with a proficient understanding of what "safe remediation" actually requires 

• A track record of contributing to a shared skill or tool library consumed by multiple agents 

Meet Your Team

As part of SAP’s Global Cloud Operations Cloud Lifecycle Engineering & AI Ops organization, you’ll join a team responsible for developing AI solutions related to operations of SAP’s strategic cloud solutions, such as SAP Business AI Platform, Joule, Business Data Cloud and AI Platform Our mission is evolving beyond traditional cloud operations. We are embracing automation, intelligent observability, AIOps, and AI agents to build the next generation of cloud operations. Our engineers partner closely with development and platform engineering to create smarter operational workflows, reduce time to resolution, and continuously improve customer experience. If you’re excited about cloud technologies, enjoy solving complex problems through AI , and want to help shape the future of AI-enabled operations at SAP, we’d love to meet you.