Roles and Responsibilities
- Design, build, and maintain enterprise-grade ELT and ETL processes handling large data volumes using Python, PySpark, Kafka, and Databricks.
- Develop and deploy Gen AI agents using Google ADK, Google Flash 2.5+ LLMs, and Human-in-the-Loop (HIL) architecture.
- Build data federation layers supporting Data Mesh architectures with Starburst to enable machine learning, deep learning, and NLP use cases.
- Develop, deploy, and automate microservice integrations on cloud-native infrastructure using OpenShift or Kubernetes with automated CI/CD pipelines.
- Integrate agentic AI tools (Devin.AI, GitHub Copilot) and Model Context Protocol (MCP) using advanced prompt engineering to boost development efficiency.




- Ensure strict data quality, governance, risk assessments, and regulatory compliance across all engineered data lifecycles.

Preferred Candidate Profile
- Experience:
- 8+ years overall experience in large-scale application development with recent hands-on deployment of AI agents into production.
- 5+ years of experience in a Python and PySpark Engineering Lead role delivering high-volume ELT/ETL processes.
- Domain background in Banking, Cards, Mortgage, Deposits, or Wealth Management is preferred.

📌 Senior Data Engineer (India)
🏢 SG Analytics
📍 India