AI Data Engineer III

Design and build the semantic layer (metrics, dimensions, entities) on AWS data warehouse to establish a single source of truth for KPIs used by BI tools, analysts, and AI agents.

Design and implement text-to-SQL agents including retrieval, prompt strategy, query generation, validation, and evaluation pipelines to measure answer accuracy.

Define ontologies and business glossaries for the mobility domain and integrate semantic context, metadata, and lineage to make datasets agent-ready, partnering closely with data engineers, analysts, and AI platform teams.

9+ years of experience in analytics/data engineering with hands-on experience in building semantic or metrics layers and productionizing LLM-based applications like text-to-SQL or RAG systems.

Proficient in SQL and Python; experience with AWS cloud data warehouses such as Redshift, Snowflake, or Databricks; and with LLM frameworks/APIs like LangChain, Bedrock, Anthropic API.

Bachelor's or Master's degree in Computer Science or a closely related discipline (B.Tech, B.E, or Master's).

Experience with semantic or dimensional data modeling is highly desirable; knowledge of ontology standards (RDF, OWL, SKOS), knowledge graphs, or MCP-based agent context is a plus.

Experienced senior-level data engineer with deep expertise in semantic modeling and productionizing AI-driven data solutions in cloud environments (AWS).

Comfortable working cross-functionally across engineering, analytics, and AI platform teams, evangelizing semantic modeling best practices and mentoring engineers.

Up-to-date with emerging semantic layer engines, knowledge graphs, and LLM technologies, capable of driving build-vs-buy decisions and adopting engineering best practices including Git, CI/CD, testing, and code reviews.