Join our team as a Custom Software Engineer, focusing on developing AI-native, data-centric products on SAP BTP Datasphere. This role leverages strong enterprise data warehousing and semantic modeling expertise with agentic AI architectures. The goal is to create intelligent data experiences, including data agents, conversational analytics, and grounded insights, built upon governed Datasphere models and integrated enterprise sources.

SAP Datasphere serves as a robust data warehousing solution with extensive integration capabilities, providing the foundation for innovative data products.

Design and implement governed data products within Datasphere, utilizing concepts like Spaces and shareable models. Build semantic models suitable for both analytics and AI consumption, ensuring clear entity definitions and lineage.

Develop grounded AI experiences by connecting LLM applications to curated Datasphere models and enterprise sources. Engineer effective retrieval strategies that adhere to domain boundaries, freshness requirements, and access controls for reliable AI outputs.

Facilitate hybrid modernization and migration paths from legacy warehouse investments using approaches like BW bridge patterns. Implement lakehouse-style layering (e.g., Bronze/Silver/Gold) for data landing, cleansing, and publishing analytics-ready models, embedding quality controls throughout the delivery lifecycle.

Construct data agents capable of planning, tool invocation, context retrieval, and answer generation with citations. Establish evaluation and observability loops for conversational analytics and data agents, incorporating telemetry for reliability and cost efficiency.

Collaborate closely with business, data governance, and platform teams to align data products with strategic decisions and operational workflows. Drive the adoption of reusable patterns and accelerators for consistent delivery across domains.

A minimum of 3 years of experience is required for this role. Candidates must possess strong data warehousing fundamentals and the ability to translate business domains into governed analytical models. Proficiency in building with LLMs, including RAG, retrieval, grounding, prompt/tool design, and evaluation, is essential.

Solid software engineering fundamentals are expected, encompassing testability, a CI/CD mindset, and experience with reliable integrations. Familiarity with migration/modernization experience using BW bridge style transition patterns and layered architecture implementation is strongly beneficial. Experience with vector search and embedding pipelines for integrating external AI retrieval components is also advantageous.