Overview
Title: Data Engineer
Duration: 6 Months initially
Location: Bangalore
Looking for a professional in designing and deploying GenAI and data-driven solutions on Snowflake. The role requires expertise in Snowflake data engineering, agentic AI workflows (LangChain/LangGraph), and building scalable data pipelines and ML integrations using Snowpark.
Responsibilities
Design and optimize data models, schemas, and pipelines in Snowflake (raw, staging, curated layers).
Prepare architecture diagrams for solutions on Snowflake.
Build and maintain ELT/ETL workflows using Snowpipe, Streams, Tasks, and external orchestration tools.
Integrate Agentic AI workflows (LangChain, LangGraph, etc.) with Snowflake as the primary data backbone.
Enable AI agents to query, reason, and act using Snowflake datasets, including secure read/write operations.
Implement batch and real-time data processing pipelines in Snowflake.
Deploy and manage ML models via Snowpark for advanced analytics and AI-driven insights.
Ensure data governance, RBAC, and compliance across all Snowflake environments.
Monitor and optimize warehouse performance, cost efficiency, and query execution.
Take ownership of modules, guide team members and interact with clients.
Required Skills
Strong expertise in Snowflake Data Cloud (SQL, schema design, performance tuning).
Hands-on experience with Snowpipe, Streams, Tasks, Clustering, and Partitioning.
Proficiency in Python and SQL for data engineering and AI workflows.
Experience with LangChain, LangGraph, or other agentic AI frameworks.
Knowledge of data governance, RBAC, and security best practices in Snowflake.
Ability to build scalable ELT/ETL pipelines for structured and semi-structured data.
Familiarity with Snowpark for deploying ML/AI models.
Note: Need an immediate joiner only