Job Summary

Seeking a Senior AI / GenAI Lead with strong hands-on experience in Document Intelligence, enterprise RAG, vector search, semantic modeling, and Knowledge Graphs. The role will design scalable AI knowledge-retrieval solutions combining Apache Iceberg, Apache Ossie, vector embeddings, graph retrieval, and structured metadata.

Key Responsibilities

Build document ingestion and NLP pipelines covering OCR, parsing, chunking, classification, metadata/entity extraction, and semantic enrichment.Use Apache Iceberg as a governed storage layer for document chunks, metadata, and vector embeddings.Design embedding, vector indexing, similarity/ANN search, metadata filtering, hybrid search, and reranking solutions.Develop semantic models using Apache Ossie for datasets, relationships, metrics, business concepts, and AI context.Design Knowledge Graphs and graph-based retrieval using GQL/Cypher or equivalent.Use Python and NetworkX for graph construction, traversal, relationship analysis, centrality, and community detection.Build advanced hybrid RAG solutions combining vector search, semantic models, Knowledge Graphs, and structured metadata.Design retrieval architectures for enterprise GenAI and agentic AI applications.

Skill Requirements

Document Intelligence, NLP & OCRApache IcebergApache Ossie / Semantic LayerVector Embeddings & Similarity SearchRAG / Hybrid Retrieval / RerankingKnowledge Graphs & GQL/CypherPython & NetworkXGraph AnalyticsMetadata & Entity ExtractionLLM / GenAI / Agentic AI integration

Other Requirements

Strong hands-on AI/data engineering background with experience designing production-grade enterprise RAG and knowledge-retrieval platforms. Ability to work across document processing, lakehouse/data architecture, NLP, vector retrieval, semantic modeling, and graph technologies.Skill Keywords: GenAI | RAG | Document Intelligence | NLP | Apache Iceberg | Apache Ossie | Vector Search | Embeddings | Knowledge Graph | GQL | Cypher | Python | NetworkX | Hybrid Search | Agentic AI