Data Engineer

Experience: 3-6 years

Opening: 3-4

Location: Pune

Skillsets: Job Description:

Skills - Data Warehouse / Semantic Layer / Business expertise

Role Overview:

We are building a Semantic Data Layer that powers AI agents and marketing use cases by grounding

them in trusted, governed enterprise data. This layer sits on top of our data products and translates raw

data into business-ready, AI-consumable semantic objects — metrics, dimensions, entities, KPIs, and

relationships — with full lineage, governance, and explainability.

You will own the end-to-end engineering of this layer: from designing the semantic data models on top

of an enterprise data warehouse, to building ingestion and transformation pipelines, to operationalizing

semantic endpoints that downstream AI agents, BI tools, and analytics applications consume. You will

work alongside AI engineers, data architects, and product owners to ensure the layer scales reliably and

produce consistent, explainable outputs

Key Responsibilities:

• Design and build the semantic data layer on top of a cloud data warehouse (Snowflake / Databricks /

BigQuery / Redshift), including conformed dimensions, fact models, KPI/metric definitions, and reusable

business entities

• Develop and maintain ingestion, transformation, and orchestration pipelines that feed the semantic

layer from upstream data products

• Implement business rules, calculation logic, and data quality checks for KPIs and metrics so that

downstream consumers see consistent, certified outputs

• Build and operationalize semantic endpoints (governed APIs, SQL views, semantic models in tools like

dbt / Cube / AtScale / LookML) for AI agents, BI dashboards, and self-service analytics

• Establish lineage, versioning, and traceability across the layer so every metric and entity can be traced

back to its source

• Partner with AI engineers to ensure semantic outputs are structured for AI consumption (grounding,

retrieval, knowledge graph linkage)

• Set up monitoring, alerting, and DQ benchmarking for ongoing health of the semantic layer

• Contribute to schema evolution, metric drift detection, and ontology updates as the business evolves

• Mentor junior engineers and uphold engineering standards (naming conventions, pipeline patterns,

code review)

Must-Have Skills (Data Engineering Core):

• Data Warehousing & Modeling

• Pipeline Engineering

• Data Quality & Governance

• Cloud & DevOps

• Semantic Modeling

Good-to-Have Skills (Data Architecture / Semantic Modeling Stretch):

• Knowledge Graphs & Ontologies

• AI / LLM Context Engineering

• Architecture Thinking