Senior Data Engineer - AI Retrieval Platforms

Capgemini; Hyderabad, Pune District, Bengaluru; On-site; INR 2,400,000 - 4,200,000; Full time

Job summary

Capgemini in Hyderabad seeks an experienced Senior Data Engineer to build and manage enterprise-scale Knowledge Graphs, AI retrieval systems, and data platforms powering next-generation AI agents.

You will design semantic data models, develop ETL pipelines, implement Graph-RAG solutions, and optimize vector search across PostgreSQL, Neo4j, and ClickHouse while ensuring data governance and security.

Qualifications

• 10+ years of Data Engineering experience.
• Strong hands-on expertise in Python and SQL.
• Proven experience with Neo4j or similar Graph Database.
• Strong understanding of Knowledge Graphs, Ontologies, and Graph Query Languages.
• Experience designing and operating RAG (Retrieval-Augmented Generation) platforms.
• Hands-on experience with Embeddings, Vector Search, Hybrid Search, and Reranking.
• Experience building large-scale ETL/ELT pipelines.
• Knowledge of Data Governance, PII/PHI compliance, and data security controls.
• Experience with Kubernetes-based deployments and cloud-native architectures.

Responsibilities

• Design, develop, and maintain enterprise-scale Knowledge Graphs and semantic data models.
• Build entity resolution frameworks for matching customers, organizations, claims, policies, and accounts across multiple systems.
• Develop scalable data ingestion and transformation pipelines from various client systems.
• Implement Graph Retrieval and Graph-RAG solutions for AI agents.
• Build and optimize vector search, hybrid search, embedding pipelines, and reranking frameworks.
• Ensure data quality, lineage, governance, monitoring, and auditability.
• Design permission-aware retrieval systems with tenant isolation and document-level security.
• Develop agent memory and retrieval frameworks supporting episodic and precedent memory.
• Collaborate with AI, Product, and Platform teams to establish common data contracts and standards.
• Optimize performance across PostgreSQL, Neo4j, ClickHouse, and vector search platforms.

Skills

Data engineering

Python

SQL

Graph databases

Knowledge graphs

RAG

Embeddings

Vector search

ETL/ELT pipelines

Data governance

Tools

Neo4j

PostgreSQL

ClickHouse

Neo4j

Job description

We are looking for an experienced Senior Data Engineer to build and manage enterprise-scale Knowledge Graphs, AI Retrieval Systems, and Data Platforms that power next-generation AI agents. The ideal candidate will have strong expertise in Graph Databases, Data Engineering, RAG Architecture, Entity Resolution, and Regulated Data Management.

Responsibilities

• Design, develop, and maintain enterprise-scale Knowledge Graphs and semantic data models.
• Build entity resolution frameworks for matching customers, organizations, claims, policies, and accounts across multiple systems.
• Develop scalable data ingestion and transformation pipelines from various client systems.
• Implement Graph Retrieval and Graph-RAG solutions for AI agents.
• Build and optimize vector search, hybrid search, embedding pipelines, and reranking frameworks.
• Ensure data quality, lineage, governance, monitoring, and auditability.
• Design permission-aware retrieval systems with tenant isolation and document-level security.
• Develop agent memory and retrieval frameworks supporting episodic and precedent memory.
• Collaborate with AI, Product, and Platform teams to establish common data contracts and standards.
• Optimize performance across PostgreSQL, Neo4j, ClickHouse, and vector search platforms.

Mandatory Requirements

• 10+ years of Data Engineering experience.
• Strong hands-on expertise in Python and SQL.
• Proven experience with Neo4j or similar Graph Database.
• Strong understanding of Knowledge Graphs, Ontologies, and Graph Query Languages.
• Experience designing and operating RAG (Retrieval-Augmented Generation) platforms.
• Hands-on experience with Embeddings, Vector Search, Hybrid Search, and Reranking.
• Experience building large-scale ETL/ELT pipelines.
• Knowledge of Data Governance, PII/PHI compliance, and data security controls.
• Experience with Kubernetes-based deployments and cloud-native architectures.