AI Data Engineer

Role: AI Data Engineer

Experience: 6+ years in Data Engineering, with 2+ years in AI/ML Data Pipelines

Location: Pune

Role Overview:

We are looking for an AI Data Engineer to build and optimize data pipelines for AI solutions, including RAG, vector search, and enterprise knowledge graphs.

Key Responsibilities:

• Build pipelines for structured and unstructured data ingestion and transformation.
• Develop chunking, embedding, RAG, and vector search pipelines using Azure AI Search.
• Build enterprise knowledge graphs, ontologies, and GraphRAG solutions.
• Ensure data quality, lineage, metadata, security, and access controls.
• Manage pipeline monitoring, refresh, and reconciliation.

Requirements & Qualifications:

• 6+ years in data engineering, including 2+ years in AI/ML data pipelines.
• Strong Python, SQL, and Azure data services skills.
• Experience with Azure AI Search, embeddings, vector databases, and RAG.
• Knowledge of graph databases, ontologies, and semantic modelling.
• Understanding of data governance, lineage, and access controls.

Key Deliverables:

• Data pipelines and source-to-target mappings
• Data quality and lineage documentation
• Vector data and knowledge graph solutions

👉 Interested? Share your CV at rudrakshi.jain@zidea.tech