Senior Developer - Java/LLMs/RAG/AI Agents (7-12 years)

We help the world run better At SAP, we keep it simple: you bring your best to us, and we'll bring out the best in you. We're builders touching over 20 industries and 80% of global commerce, and we need your unique talents to help shape what's next. The work is challenging – but it matters. You'll find a place where you can be yourself, prioritize your wellbeing, and truly belong. What's in it for you? Constant learning, skill growth, great benefits, and a team that wants you to grow and succeed.       What you'll bring •    You have deep experience in distributed systems and scalable application design, with strong hands-on skills in LLMs, advanced RAG patterns, and agentic workflows.  •    Experience building agentic workflows on SAP AI Core and integrating LLM-based features into CAP Java applications is expected.  •    Proficiency in system design for scale, resiliency, and fault tolerance is required.  •    Strong experience in performance optimization, cost management, and troubleshooting complex production systems is essential.  •    A solid understanding of SRE principles, observability (logs, metrics, tracing), and incident management is expected — including Open Telemetry instrumentation and SAP Cloud Logging dashboards.  •    Experience designing evaluation frameworks for AI systems, validating model behavior, and applying agentic engineering patterns is critical.  •    You use Claude-style tools to generate code and ideas, but you read and challenge their output — you know when the AI is making the wrong call in both code and design.  •    Familiarity with multi-tenant SaaS architecture on SAP BTP (MTX, service-manager, IAS/AMS) is a strong advantage.  Four values matter at every level: 1.    Learning agility (non-negotiable, and the most important value) — you rapidly pick up new models, frameworks, SAP Technologies, ontologies, and industry processes. You enjoy updating your mental model as the landscape shifts, which it will, frequently. 2.    Bias for action — you move quickly from ambiguity to a working prototype and learn through execution. 3.    Critical thinking — you ask the right questions, so we stay focused on the objective instead of just managing the day. 4.    End-to-end ownership — you own the outcome from problem definition through build, deployment, and evaluation.   What you'll build •    You'll independently design and architect scalable, AI-native application systems and components, including advanced RAG pipelines and multi-agent workflows.  •    You'll design and build AI agents integrated into GHRA's revenue accounting domain — including formula explanation, disposition computation assistance, and production volume analysis — using SAP AI Core and CAP Java.  •    You'll contribute to the design of ontology-grounded agents for the domain, encoding accounting rules, formula structures, and ownership relationships as structured knowledge that agents can reason over reliably, rather than relying on prompt-only approaches.  •    Evaluation and benchmarking frameworks to measure AI system quality, reliability, and performance are things you'll build and own. This includes domain-specific test harnesses that validate LLM outputs against known good formula  results and accounting rules — and the honest memo that explains why an idea shouldn't ship. •    You'll optimize latency, throughput, and cost efficiency across systems — including HANA Cloud query optimization and AI Core inference cost management.  •    Observability and SRE practices, including monitoring, alerting, incident response, and root cause analysis, are areas you'll implement and improve — specifically enabling OTEL tracing across the CAP microservice fleet and building Cloud Logging dashboards for cross-service visibility.  •    You'll partner with platform, data, and AI teams to design robust, production-ready