Data & AI Engineer - Technical Lead / Architect

We are looking for a Data & AI Engineer to build scalable data pipelines and LLM-ready context stores. You will use Snowflake and dbt to transform raw enterprise data into clean models and power downstream Retrieval-Augmented Generation (RAG) and GenAI applications.

Key Responsibilities

• Design modular, tested dbt models running on Snowflake for structured metrics and semantic search.
• Build automated RAG pipelines handling data ingestion, text chunking, and embedding generation (using Snowpark, Cortex, or vector databases).
• Optimize Snowflake virtual warehouses, dynamic tables, and query performance for low-latency retrieval.
• Enforce dbt testing, documentation, and data quality standards for AI/BI consumers.
• Build and maintain CI/CD pipelines (Git, GitHub Actions, dbt Cloud).

Required Skills

• Experience in Data Engineering / Analytics Engineering.
• Snowflake: Snowpark, Dynamic Tables, Tasks, micro-partitioning, and JSON/semi-structured parsing.
• dbt: Jinja macros, incremental models, semantic layer, unit/data testing.
• RAG / GenAI: Vector embeddings, similarity search, text chunking strategies, LangChain/LlamaIndex or Snowflake Cortex AI.
• Languages: Advanced SQL and Python.