Data/ AI Engineer - All Levels
Summary
Build and own a modern AI-native data platform using Cube.js, LLMs, and vector databases to power analytics and AI agents for a new client team.
Overview
We are building a new AI team from the ground up for our client. This is a greenfield opportunity to build an AI-native data platform powered by Cube.js and modern semantic workflows. You will be part of the founding team defining architecture, not just maintaining it.
Responsibilities
- Design and build scalable data pipelines and semantic layer using Cube.js / Cube Cloud
- Build LLM-powered applications on top of the semantic layer - RAG, AI agents, intelligent analytics
- Develop and optimize data models, metrics layer and headless BI APIs
- Integrate vector databases, LLMs and knowledge graphs for semantic search and reasoning
- Collaborate with AI Scientists and Product to take models from prototype to production
- Own performance, governance and security of the semantic layer
Required Skills
- Experience in Data Engineering / AI Engineering with Python and SQL
- Hands-on experience with Cube.js or similar semantic layer - dbt Semantic Layer, LookML, AtScale
- Strong experience with LLMs, RAG, LangChain / LlamaIndex, Vector DBs
- Experience with data warehouses - Snowflake / BigQuery / Redshift
- Experience with ETL/ELT, API development and data modeling
Nice to Have
- Experience with Knowledge Graphs, GraphQL
- Experience with LLMOps, Docker, Kubernetes
- Experience with GenAI evaluation and fine-tuning