About the role

Data Engineer – Snowflake & AI Analytics

We are looking for a Data Engineer with strong hands-on experience in Snowflake Data Warehouse and exposure to AI-driven analytics solutions.

The role focuses on building scalable data pipelines, implementing optimized data models, and contributing to AI-powered applications such as conversational analytics using Snowflake Cortex LLM.

This is a delivery-focused role with growing technical ownership and business exposure.

Key Responsibilities

Snowflake Data Engineering
- Develop and maintain data models (Star schema / Snowflake schema).
- Build and optimize ELT pipelines within Snowflake.
- Write efficient SQL transformations and performance-tuned queries.
- Support data ingestion from structured and semi-structured sources.
- Assist in warehouse sizing, clustering, and cost optimization.
- Implement role-based access control (RBAC) and basic data governance practices.
AI & Cortex LLM Implementation Support
- Support development of AI agents using Snowflake Cortex LLM.
- Assist in building Retrieval-Augmented Generation (RAG) workflows.
- Work on vector embeddings and semantic search implementations.
- Participate in prompt engineering and testing.
- Validate and test AI-generated outputs for accuracy and security.
Conversational & Analytics Solutions
- Contribute to building conversational analytics tools enabling natural language queries.
- Support integration of data models with BI tools (Power BI / Tableau).
- Translate functional KPIs into data models and dashboards.
- Ensure data accuracy, consistency, and performance.
Collaboration & Delivery
- Work closely with Senior Leads and Architects on design implementation.
- Participate in sprint planning and Agile ceremonies.
- Document data models, transformations, and solution components.
- Provide production support and troubleshooting.

Required Qualifications

5–7 years of experience in Data Engineering / Analytics Engineering.
3–4 years hands-on experience with Snowflake.
Strong SQL expertise (advanced joins, window functions, performance tuning).
Working knowledge of Python.
Understanding of data modeling concepts (Dimensional modeling preferred).
Exposure to AI/LLM platforms (Snowflake Cortex or similar is a plus).
Experience integrating with BI tools (Power BI / Tableau).

Preferred Qualifications

Exposure to RAG frameworks or semantic search.
Basic understanding of data governance and security models.
Experience working with semi-structured data (JSON, Parquet, etc.).
Domain exposure in HR, Sales, Finance, or Supply Chain analytics.