AI Data Engineer [T500-28265]

Comply; Ernakulam; On-site; INR 900,000 - 1,400,000; Full time

Job summary

COMPLY is seeking an AI Data Engineer to implement its semantic layer and translate ontological models into production knowledge graphs and vector pipelines. You will work with data engineers, ontologists, and backend teams to ensure AI-ready data products are reliable and scalable.

You will design embedding pipelines, operate vector databases, and implement RAG architectures to ground LLM outputs in COMPLY’s data. Experience with graph DBs and cloud platforms is essential.

Qualifications

• Hands-on role implementing JSON-LD semantic models into production data systems.
• Experience building knowledge graphs and graph databases.
• Familiarity with semantic web standards such as JSON-LD, RDF, OWL, SKOS.
• Experience with cloud data platforms (AWS, Azure, or GCP).
• Strong Python and data pipelines experience.

Responsibilities

• Implement JSON-LD semantic models designed by ontologists into production data systems.
• Build and maintain knowledge graph structures reflecting canonical domain models.
• Develop graph database schemas, queries, and data ingestion pipelines.
• Design and implement embedding pipelines for vector space representations.
• Build and operate vector database infrastructure for semantic search and similarity retrieval.
• Implement RAG architectures that ground LLM outputs in the data.
• Collaborate with data and backend teams to embed semantic models into APIs.

Skills

Python

Data engineering

Knowledge graphs

Graph databases

Semantic layer

LLM integration

Vector databases

DataOps

Cloud platforms

Domain-driven design

Ontology collaboration

Education

Bachelor's degree in Computer Science or related

Tools

Neo4j

Jena Fuseki

Amazon Neptune

Pinecone

Weaviate

Qdrant

pgvector

Job description

COMPLY is the world’s leading aggregator of financial and regulatory data to support compliance. Our mission is to help financial institutions meet their regulatory obligations with confidence, clarity, and speed. We ingest, process, and enrich vast volumes of complex, high-variance data from hundreds of brokers, data providers and other sources of information across the US and beyond. The scale, diversity, and importance of this data creates unique technical challenges and opportunities for innovative engineers.

The COMPLY Data Platform is a strategic initiative at the heart of this mission. We are building a modern, cloud‑native semantic layer from the ground up — using JSON‑LD as our semantic language — to power AI‑driven insights, regulatory analytics, and next‑generation data products.

Our AI Data Engineers work hand‑in‑hand with the data engineers, architects, and ontologist to translate semantic models into production‑grade knowledge graphs, embedding pipelines, and RAG architectures that make Comply’s data genuinely AI‑ready.

The Role:

We are looking for an AI Data Engineer to implement and operationalize Comply’s semantic layer — turning the ontological models defined by our ontologist and architects into working knowledge graphs, vector search infrastructure, and LLM‑powered pipelines. This is a hands‑on engineering role at the intersection of knowledge representation, AI infrastructure, and data platform engineering. You will own the delivery of semantic layer components, collaborate closely with application and data engineering teams, and ensure that AI‑ready data products are reliable, performant, and adopted in practice. You will report into the Data and Analytics organization as part of a new team being created to enable future data capabilities in relation to our AI ambitions.

Key Responsibilities:

Semantic Layer Implementation

• Implement JSON‑LD‑based semantic models designed by the ontologist into production data systems
• Build and maintain knowledge graph structures that reflect canonical domain models
• Develop and manage graph database schemas, queries, and data ingestion pipelines
• Ensure semantic consistency between ontology definitions and downstream data products AI & Vector Infrastructure
• Design and implement embedding pipelines that represent Comply’s financial and regulatory data in vector space
• Build and operate vector database infrastructure for semantic search and similarity retrieval
• Implement RAG (Retrieval‑Augmented Generation) architectures that ground LLM outputs in Comply’s proprietary data
• Evaluate and integrate LLM tooling and frameworks appropriate to Comply’s use cases Data Pipeline & Platform Engineering
• Build reliable, observable data pipelines that feed the semantic layer from upstream broker and regulatory data sources
• Apply DataOps practices including testing, monitoring, lineage tracking, and SLAs
• Work with Data Engineers and Backend Engineers to embed semantic models into APIs and data contracts
• Ensure the semantic layer scales with data volume and platform growth Collaboration & Enablement
• Partner closely with the Ontologist to ensure implemented models faithfully reflect domain intent
• Support consuming application teams in understanding and adopting AI‑ready data products
• Contribute to resolving cross‑domain data integration challenges
• Strong hands‑on experience in data engineering, with a focus on semantic or AI data infrastructure
• Experience building and operating knowledge graphs or graph databases (e.g. Jena Fuseki, Neo4j, Amazon Neptune, or equivalent)
• Experience with vector databases and embedding pipelines (e.g. Pinecone, Weaviate, Qdrant, pgvector)
• Practical experience implementing RAG architectures or LLM‑integrated data pipelines
• Familiarity with semantic web standards — JSON‑LD, RDF, OWL, or SKOS
• Strong Python skills and experience with data pipeline frameworks
• Experience with cloud‑native data platforms (AWS, Azure, or GCP)
• Exposure to domain‑driven design (DDD) and bounded contexts
• Experience working directly with ontologists or knowledge engineers
• Familiarity with data contracts and data product frameworks
• Experience with DataOps tooling, data reliability, or data observability platforms
• Background in financial services, RegTech, or compliance data

Way of Working:

• Collaborative and pragmatic — focused on adoption and delivery, not theoretical completeness
• Comfortable working across engineering and domain boundaries
• Able to translate semantic and ontological concepts into concrete engineering decisions
• Confident navigating greenfield environments where architecture is still being defined

Impact and Outcomes:

• A production‑grade semantic layer that is consistent, scalable, and used in practice by consuming teams
• Embedding and vector infrastructure that enables Comply’s AI‑powered data products
• Reliable, observable pipelines that maintain semantic quality from ingestion through to consumption
• Reduced time‑to‑value for new AI features through reusable semantic infrastructure