Senior Data Engineer

Role overview

Ciklum is hiring a Senior Data Engineer to design and develop the core data foundation for the Tango Agent Development Platform (ADP). The position is central to powering autonomous AI agents such as the Lease Abstraction and CAM Reconciliation agents with secure, highly accurate, schema-aligned data that supports reliable reasoning.

In this role, you will act as the main Data Engineer for the Tango initiative. Your work will focus on converting the client’s complex relational source systems into an agent-ready data layer. You will create ETL pipelines and materialized views that let agents access data safely through the Model Context Protocol (MCP), so that AI models do not interact with raw databases directly, reducing both hallucination risk and security exposure.

Ciklum is a global digital services and software engineering company working with major enterprise and fast-growing clients worldwide. The team brings together thousands of engineers, designers, product managers, and data specialists to deliver tailored digital solutions and support large-scale digital transformation initiatives.

Key responsibilities

• Build the data engine by designing and implementing ETL and ELT processes that extract, cleanse, and shape proprietary real estate data into secure, structured views for agent use.
• Set up and optimize a multi-layer data architecture that includes PostgreSQL for relational workloads, ChromaDB or PGVector for embeddings, and Neo4j-based graph storage for relationship mapping.
• Create and support MCP adapters and protected SDK endpoints so agents access governed interfaces instead of connecting directly to databases.
• Develop the initial knowledge graph from client data to represent relationships across leases, entities, and CAM charges.
• Establish and maintain the RAG knowledge base, including ingestion pipelines and metadata handling for lease abstracts and historical documents.
• Implement strong logical data isolation controls to support multi-tenant security and prevent data leakage across tenants on the shared platform.

Required background

• Strong command of data engineering, including production-grade ETL and ELT development with Python and SQL; dbt experience is a strong advantage.
• Practical exposure to vector databases such as Chroma and PGVector, along with graph databases like Neo4j or Cognee for AI-driven solutions.
• Proven experience working with AWS data services, especially RDS, S3, and event-driven architecture patterns.
• Experience building data systems that align with SOC 2 and GDPR requirements, including masking approaches and zero-trust access design.
• Understanding of commercial real estate data structures such as leases, CAM, and invoices is a major plus.
• Comfort working with orchestration tools such as Temporal for long-running workflows is desirable.
• Awareness of how data supports agentic frameworks such as LangChain or LangGraph is desirable.

Eligibility

Any graduate can apply for this role.

Additional information

This is a full-time position based in Pune, India. The compensation range is INR 15,00,000 to INR 30,00,000 per year.

The role involves contributing to a platform designed for secure, governed data access for autonomous AI agents, with an emphasis on reliability, privacy, and scalable architecture.