At SIXT, we are building the semantic foundation that lets AI agents and thousands of analysts query our data platform reliably in natural language. As Senior Analytics/Data Engineer in our Data Platform team, you design the semantic layer and ontologies on top of our AWS-based data platform and build the text-to-SQL agents that turn them into business value. You will join a team of 30 data engineers building the data platform for analytics and AI agents across the SIXT group, working with state-of-the-art LLM technology to shape how our business interacts with data, apply now and become part of Team Orange

Responsibilities

- You define and build our semantic layer (metrics, dimensions, entities) on top of the AWS data warehouse, creating a single source of truth for KPIs consumed by BI tools, analysts, and AI agents
- You design and implement text-to-SQL agents on the data warehouse, from retrieval and prompt strategy over query generation and validation to evaluation pipelines that measure answer accuracy
- You specify ontologies and business glossaries for the mobility domain (rental, fleet, pricing, customer) and publish them in machine-readable form so agents and services can consume them
- You integrate semantic context, metadata, and lineage from our data catalogue into agent workflows, and define the standards that make datasets "agent-ready"
- You partner closely with data engineers, analysts, and our AI platform teams, evangelize semantic modeling best practices,



and mentor engineers across the platform organization
- You continuously evaluate emerging tooling (semantic layer engines, knowledge graphs, LLM frameworks) and drive build-vs-buy decisions

Your Skills Matter

- Education You have B.Tech, B.E, or Masters degree in Computer Science or a closely related discipline
- Experience You bring 9+ years in analytics/data engineering, including hands-on experience building a semantic or metrics layer (eg dbt Semantic Layer, Cube, AtScale, LookML) and productionizing LLM based applications, ideally text-to-SQL or RAG systems
- Tech Stack You are highly proficient in SQL and Python; you have worked with up-to-date cloud data warehouses (Redshift, Snowflake, or Databricks) on AWS, and with LLM frameworks and APIs (eg LangChain, Bedrock, Anthropic API)
- Semantic Modeling Your experience in dimensional and semantic data modeling is a Big plus; Knowledge of ontology standards (RDF, OWL, SKOS), knowledge graphs, or MCP-based agent context is again an advantage
- Ways of Working You work with engineering best practices (Git, CI/CD, code reviews, testing), take ownership end-to-end, and communicate complex concepts clearly to technical and business stakeholders

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 AI Data Engineer III (Bengaluru)
🏢 SIXT Research and Development
📍 Bengaluru