Data Architecture & Data Engineering – Strong experience designing scalable data architectures, data models, hands on experience with ingestion frameworks and ETL/ELT pipelines for structured, semi-structured and unstructured data. Data Pipelines for AI/Knowledge Applications – Hands-on ability to build pipelines to extract, transform, enrich, chunk and ingest documents/data into downstream data and knowledge platforms for AI/Agent consumption. Graph Databases & Data Modeling – Strong understanding of graph data modeling and hands-on experience with Neo4j or equivalent graph databases, including nodes, relationships, properties, indexing and graph-oriented query patterns. Python & API/Data Services – Strong Python development skills for building data pipelines and services, with practical experience working with FastAPI and REST APIs; ability to integrate data services with application/AI layers. PostgreSQL & Vector Data – Strong SQL/PostgreSQL skills, with working knowledge of pgVector, embeddings and vector search and how relational, vector and graph data can work together. Data Integration & Quality – Experience with data ingestion, transformation, validation, metadata, lineage, data quality and error/reprocessing mechanisms, with the ability to work closely with GenAI/Agent teams on their data requirements.
Preferred Skills:
GenAI / AI Data Architecture Exposure – Understanding of RAG, embeddings, document processing, knowledge bases and how data is prepared and served to LLM/Agent applications. GraphQL & Graph-based APIs – Experience with GraphQL, graph-oriented APIs and designing data access/query layers for application and agent consumption. Google GenAI Ecosystem – Exposure to Google Gemini, Google ADK and/or A2A frameworks, particularly from the perspective of providing data/context to AI agents. Modern Data/AI Application Stack – Exposure to technologies such as Neo4j, pgVector, FastAPI and cloud-native data platforms, with the ability to integrate multiple data stores. AI-Assisted Engineering – Experience using GitHub Copilot or similar AI-assisted development tools to accelerate data engineering and application development. Enterprise Data Architecture / BFSI – Experience designing data solutions in large-scale enterprise or regulated environments, preferably banking/financial services, with strong understanding of security, governance and data privacy.
