Job Description

At Reltio®, we believe data should fuel business success. Reltio’s AI-powered data unification and management capabilities—encompassing entity resolution, multi-domain master data management (MDM), and data products—transform siloed data from disparate sources into unified, trusted, and interoperable data. Reltio Data Cloud™ delivers interoperable data where and when it's needed, empowering data and analytics leaders with unparalleled business responsiveness. Leading enterprise brands—across multiple industries around the globe—rely on our award-winning data unification and cloud-native MDM capabilities to improve efficiency, manage risk and drive growth.

At Reltio, our values guide everything we do. With an unyielding commitment to prioritizing our “Customer First”, we strive to ensure their success. We embrace our differences and are “Better Together” as One Reltio. We are always looking to “Simplify and Share” our knowledge when we collaborate to remove obstacles for each other. We hold ourselves accountable for our actions and outcomes and strive for excellence. We “Own It”. Every day, we innovate and evolve, so that today is “Always Better Than Yesterday”. If you share and embody these values, we invite you to join our team at Reltio and contribute to our mission of excellence.

Reltio has earned numerous awards and top rankings for our technology, our culture and our people. Reltio was founded on a distributed workforce and offers flexible work arrangements to help our people manage their personal and professional lives. If you’re ready to work on unrivaled technology where your desire to be part of a collaborative team is met with a laser-focused mission to enable digital transformation with connected data, let’s talk!

Job overview

We're building Business Ontology, a new capability built on top of the Reltio Data Cloud platform and Reltio AgentFlow. Reltio provides the trusted, governed data foundation entities, relationships, and a real-time data graph — and AgentFlow provides the agentic AI layer that acts on that data. Business Ontology extends both: it captures the meaning of enterprise data (domains, business terms, and their relationships) and connects that meaning to the physical data assets across source systems, so the ontology becomes the governed, explainable context that grounds search, analytics, and AI agents. You'll do core engineering on the pipeline behind this — importing metadata from source systems, using LLMs to enrich and map it, forming a semantic graph that links physical data to business definitions, and integrating it all with the Reltio platform.

Skill required:

Pipeline & services

• Design, build, and own backend services that run the metadata, ingestion-and-generation pipeline reliably and at scale.

• Own the pipeline stages end to end — discovery, transform, load, and generation —including how they're sequenced, orchestrated, and recovered on failure.

• Define clear service boundaries and APIs so the system stays modular as new capabilities are added.

Source integration

• Implement source adapters against a common interface — connect, discover metadata, and stream records — beginning with platforms such as Databricks and Snowflake and extending to additional sources over time.

• Extract and normalize the full picture from each source: catalogs, tables, columns, data types, keys, lineage, and usage statistics.

• Keep adapters resilient to source-specific quirks, large schemas, and incremental Re-runs.

LLM-driven enrichment & mapping

• Build the LLM integration layer: prompt construction, structured-output parsing, schema validation, retries, and token / cost management.

• Implement enrichment that turns cryptic technical metadata into clear,business-readable descriptions and labels.

• Implement mapping logic that connects physical columns to business terms, with confidence scoring and supporting evidence captured for every proposal.

Semantic graph formation

• Build the logic that links physical data assets to business definitions — deterministic connections derived from ground-truth metadata, and AI-proposed connections that

require review.

• Route AI-generated proposals through a human-approval step, so trusted facts and machine suggestions are treated differently by design.

• Ensure the resulting graph is consistent, traceable, and safe to rebuild as sources Change.

Platform integration (Reltio & AgentFlow)

• Integrate with the Reltio platform to write entities, relationships, and graph structures,with idempotent, re-runnable loads.

• Apply the platform's governance, provenance, and survivorship model so human-curated meaning always takes precedence over machine-generated suggestions.

• Support the consumption path — graph traversal and the interfaces that let AgentFlow agents resolve and query the ontology to answer business questions.

Reliability, quality & collaboration

• Make the pipeline observable and resilient — job orchestration, state tracking, artifact storage, and resume-on-failure.

• Establish engineering quality through testing, validation checks, monitoring, and sensible error handling across the pipeline.

• Partner closely with product, ontology modelers, and data stewards to turn the design into a shippable, maintainable service, and help shape technical direction as the capability grows.