This role involves designing, coding, and enhancing custom software components and applications. You will leverage modern frameworks and agile methodologies to deliver scalable, high-performance solutions precisely tailored to specific business requirements. The focus is on building AI-native, HANA-optimized SAP applications and extensions.

You will combine deep ABAP on HANA engineering expertise with agentic AI patterns, including LLMs, tools, retrieval, and evaluation. The goal is to deliver production-grade solutions that utilize HANA pushdown principles and modern ABAP, incorporating governed AI capabilities for reasoning, context retrieval, and acting within enterprise SAP workflows. This position does not involve training foundation models from scratch.

Develop ABAP solutions optimized for SAP HANA, emphasizing performance and pushdown principles. Build efficient data models using CDS views and implement performance-critical logic with AMDP/SQLScript. Write modular, testable, and maintainable ABAP code following clean architecture practices and secure coding standards. Design reusable data artifacts for various consumers and enable AI experiences by integrating ABAP services with LLM capabilities, including tool calling and retrieval grounding.

Implement automated tests for ABAP services and data artifacts. Establish evaluation harnesses for AI behaviors and introduce guardrails for AI outputs. Instrument services with logs, metrics, and traces for production support. Design robust error handling and support incident response with structured diagnostics. Integrate ABAP on HANA services with SAP and non-SAP ecosystems, collaborating with cross-functional teams for end-to-end solution delivery.

A strong foundation in ABAP Development on HANA is essential, with expertise in performance tuning, pushdown techniques, and efficient SQL access patterns. Proficiency in CDS views and modern data modeling, including associations, annotations, and authorization concepts, is required. Experience with AMDP/SQLScript for performance-critical scenarios is necessary. A solid software engineering discipline, encompassing clean design, a testing mindset, CI/CD orientation, and production readiness, is crucial.

Capability in building AI-native solutions is a must-have, including LLM integration, retrieval grounding, tool orchestration, evaluation loops, and implementing safety boundaries. Secondary but strongly beneficial skills include OData/service design patterns, API lifecycle management, experience with cloud runtimes and enterprise integration platforms, performance benchmarking, and knowledge of SAP security and authorizations.