Embark on a role focused on building AI-native, HANA-optimized SAP applications. This position leverages deep ABAP on HANA engineering expertise alongside agentic AI patterns to deliver robust, cloud-ready solutions. You will focus on high performance and production-grade quality, utilizing HANA pushdown principles, modern ABAP, and governed AI capabilities.

The work involves reasoning, retrieving context, and assisting within enterprise SAP workflows without the need for foundational model training. The goal is to create scalable solutions that are secure, compliant, and continuously improved.

Design and develop ABAP solutions specifically optimized for SAP HANA, employing pushdown principles to maximize in-database processing. Construct efficient data models and access patterns using CDS views, associations, and annotations, implementing critical logic with AMDP/SQLScript where applicable.

Develop modular, testable, and maintainable ABAP code following clean architecture practices. Build services and APIs using modern paradigms like OData, ensuring stability and contract-first behavior. Model enterprise business entities using CDS semantics for transactional and analytical use cases.

Integrate ABAP services with LLM capabilities to create AI-enabled SAP experiences, including tool calling, retrieval grounding, and deterministic fallbacks. Implement prompts, tool schemas, and context assembly strategies to minimize hallucinations and enforce safety boundaries. Build automated tests for ABAP services and data artifacts to ensure regression coverage.

A minimum of 3 years of experience is required for this role. You must possess strong hands-on expertise in ABAP Development on HANA, including performance tuning, pushdown techniques, and efficient SQL access patterns. Proficiency with CDS views and modern data modeling practices is essential.

Experience with AMDP/SQLScript for performance-critical scenarios and controlled code pushdown is expected. A solid software engineering discipline, including clean design, a testing mindset, CI/CD orientation, and production readiness, is crucial. Experience with AI native capabilities such as LLM integration, retrieval grounding, tool orchestration, evaluation loops, and safety boundaries is a key requirement.