As a Custom Software Engineer, you will be instrumental in developing innovative custom software solutions. This role focuses on designing, coding, and enhancing components across various systems and applications.

Utilizing modern frameworks and agile methodologies, you will deliver scalable, high-performing solutions tailored to specific business requirements. The core of this position involves building AI-native, data-centric products on SAP BTP Datasphere, blending expertise in enterprise data warehousing with advanced agentic AI architectures.

The goal is to create intelligent data experiences, moving beyond traditional dashboards to offer conversational analytics, data agents, and grounded insights. These will be built upon governed Datasphere models and integrated enterprise sources, positioning SAP Datasphere as a premier data warehousing solution with robust integration capabilities.

Design and implement governed data products within Datasphere, leveraging concepts like Spaces and shareable models/views to facilitate data exploration and sharing across teams.

Construct semantic models optimized for both analytics and AI consumption, ensuring clear entity definitions, measures, hierarchies, and lineage-friendly design.

Develop grounded AI experiences by connecting LLM applications to curated Datasphere models and enterprise sources, guaranteeing that AI responses are traceable to governed data.

Engineer sophisticated retrieval strategies that respect domain boundaries, data freshness, and access controls, ensuring reliable and compliant AI outputs.

Facilitate the transition from legacy warehouse investments by utilizing patterns like SAP BW model reuse with Datasphere/BW bridge for phased cloud modernization.

Implement layered design patterns (e.g., Bronze/Silver/Gold) for data ingestion, cleansing, validation, and the publishing of analytics-ready models, while enforcing strict consumption rules.

Embed quality controls, validation checks, and reproducible transformations throughout the delivery lifecycle.

Build data agents capable of planning, tool invocation, context retrieval, and generating answers with citations, supported by deterministic checks and fallback mechanisms.

Establish offline and online evaluation loops for conversational analytics and data agents, including golden questions, regression suites, and behavior tests.

Integrate telemetry for AI interactions to monitor latency, grounding rates, and failure modes, thereby enhancing 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 to ensure repeatable and efficient delivery across various domains.

A minimum of 3 years of hands-on experience is required for this role.

Key technical proficiencies include SAP BTP Datasphere, encompassing data modeling, spaces, sharing patterns, and enterprise semantic design.

Strong foundational knowledge in data warehousing and the ability to translate complex business domains into governed analytical models are essential.

Demonstrated experience in building with LLMs and RAG, including retrieval, grounding, prompt design, tool design, and evaluation.

Solid grasp of software engineering fundamentals such as testability, a CI/CD mindset, and building reliable integrations is expected.

Additional beneficial skills include migration/modernization experience with BW bridge style transition patterns and layered architecture implementation (Bronze/Silver/Gold).

Familiarity with vector search and embedding pipelines for integrating external AI retrieval components is also advantageous.