SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Reltio, an SAP Company, is building an Enterprise AI Hub to engineer the "Reltio Brain"—a Context Intelligence Operating System that transforms fragmented institutional knowledge into governed, autonomous action. As Senior AI Engineer for Data Pipelines & Context Systems, you will architect and implement the data, context, and tooling foundation that enables Reltio's AI systems and embedded AI Business Partners to operate safely and effectively across enterprise knowledge.
Your primary focus is engineering the backend systems that power intelligent data orchestration, not front-end UI. You will design production-grade pipelines that ingest, normalize, enrich, and synchronize structured and unstructured enterprise data from sources including Reltio's MDM platform, Google Workspace, Slack, Jira/Confluence, transcripts, product systems, and operational datasets. You'll build patterns for incremental indexing and vector updates that preserve lineage, permissions, and source metadata while enabling AI systems to refresh only what has changed.
You will model context boundaries across personal, team, departmental, and enterprise layers, ensuring AI systems understand data provenance, relevance, and access controls. You'll build secure MCP/API-style tools and services that expose enterprise data and actions to LLM workflows with clear schemas, guardrails, and audit trails. This includes implementing OAuth/SSO, RBAC/ABAC, tenant boundaries, and server-side permission checks to ensure retrieval and tool execution respect enterprise access controls.
Retrieval quality is critical. You will design RAG systems combining semantic search, keyword search, metadata filters, reranking, and structured queries to assemble reliable context. You'll define chunking, embedding, tagging, and provenance strategies that make responses traceable back to source documents, records, transcripts, or systems of record. You'll monitor freshness, data quality, duplicates, stale content, hallucination risk, and missing-context failure modes.
You will build harnesses for testing prompts, retrieval pipelines, tool calls, structured outputs, and agentic workflows before production deployment. You'll create evaluation datasets, acceptance criteria, observability, and regression checks for context quality, tool accuracy, latency, cost, and safety. You'll leverage modern AI coding assistants like Claude Code and Cursor to accelerate implementation while maintaining engineering discipline, security, and review standards.
The role includes human-in-the-loop operations: building review surfaces for administrators and operators to validate, correct, and improve AI outputs and context quality over time. You'll work cross-functionally with product, data science, and operations teams to ensure the platform scales reliably and safely.
