Backend Data / RAG Engineer in New York, NY 10036 (Hybrid)

· Build document ingestion, parsing, chunking, metadata extraction, embedding, indexing, and versioning pipelines.

· Implement RAG services using vector search, keyword search, hybrid retrieval, metadata filters, reranking, and citations.

· Integrate with Azure AI Search, pgvector, Pinecone, Weaviate, Qdrant, Milvus, Elasticsearch, OpenSearch, or similar platforms.

· Build APIs for retrieval, source traceability, ingestion status, feedback capture, and citation support. Implement permission-aware retrieval, RBAC, tenant isolation, audit logging, PII handling, and secure data access.

· Support retrieval quality evaluation, grounding, hallucination reduction, client demos, UAT, and production readiness.

Do you have experience in Search engines?, · Strong backend/data engineering using Python, Java, Node.js, or .NET. Strong SQL and database experience.

· Minimum 2 years hands-on AI/RAG implementation experience.

· Experience with embeddings, vector search, hybrid search, document ingestion, and RAG pipelines.

· Experience with Azure AI Search, pgvector, Pinecone, Weaviate, Qdrant, Milvus, Elasticsearch, OpenSearch, or equivalent.

· Understanding of chunking, retrieval tuning, reranking, context assembly, citations, and retrieval evaluation. BFSI, banking, insurance, capital markets, payments, or regulated enterprise experience. Client implementation experience.

Preferred Skills:

· Azure Blob Storage, Azure AI Search, Azure Document Intelligence, Azure OpenAI, or similar Azure services.

· Experience with data governance, document lineage, metadata models, knowledge graphs, or ontology-driven retrieval.

· Experience with CI/CD, containers, observability, and secure cloud deployment

Pulled from the full job description

• 401(k), * 401(k)