Senior Technical Consultant

Job Summary

• Document Intelligence & NLPHands‑on experience building document ingestion, parsing, OCR, chunking, metadata extraction, classification, entity extraction and semantic enrichment pipelines.
• Apache Iceberg Vector Store & SearchStrong experience using Apache Iceberg as the governed storage layer for document chunks, metadata and vector embeddings, with vector similarity search, indexing, filtering and retrieval over Iceberg‑backed data. Current implementations can store embeddings in Iceberg tables and perform similarity search through vector‑capable query engines, with indexes used to accelerate retrieval.
• Vector & Retrieval EngineeringExperience with embedding generation, vector indexing, similarity search, ANN concepts, metadata filtering, hybrid search, reranking and retrieval‑quality evaluation for enterprise‑scale RAG.
• Apache Ossie Semantic LayerExperience with Apache Ossie for vendor‑neutral semantic models covering datasets, fields, relationships, metrics and AI context, providing consistent business meaning to analytics and AI applications.
• Knowledge Graph & Graph QueryingExperience designing knowledge graphs and modelling relationships between documents, entities and business concepts, including GQL/Cypher or equivalent graph‑query approaches.
• NetworkX & Graph AnalyticsStrong Python and NetworkX experience for graph construction, traversal, relationship analysis, centrality, community detection and other graph algorithms.
• Hybrid Knowledge Retrieval / RAGExperience combining Iceberg vector search + semantic models + graph retrieval + structured metadata to create context‑rich retrieval for RAG and agentic AI solutions.

Key Responsibilities

• Document Intelligence & NLPHands‑on experience building document ingestion, parsing, OCR, chunking, metadata extraction, classification, entity extraction and semantic enrichment pipelines.
• Apache Iceberg Vector Store & SearchStrong experience using Apache Iceberg as the governed storage layer for document chunks, metadata and vector embeddings, with vector similarity search, indexing, filtering and retrieval over Iceberg‑backed data. Current implementations can store embeddings in Iceberg tables and perform similarity search through vector‑capable query engines, with indexes used to accelerate retrieval.
• Vector & Retrieval EngineeringExperience with embedding generation, vector indexing, similarity search, ANN concepts, metadata filtering, hybrid search, reranking and retrieval‑quality evaluation for enterprise‑scale RAG.
• Apache Ossie Semantic LayerExperience with Apache Ossie for vendor‑neutral semantic models covering datasets, fields, relationships, metrics and AI context, providing consistent business meaning to analytics and AI applications.
• Knowledge Graph & Graph QueryingExperience designing knowledge graphs and modelling relationships between documents, entities and business concepts, including GQL/Cypher or equivalent graph‑query approaches.
• NetworkX & Graph AnalyticsStrong Python and NetworkX experience for graph construction, traversal, relationship analysis, centrality, community detection and other graph algorithms.
• Hybrid Knowledge Retrieval / RAGExperience combining Iceberg vector search + semantic models + graph retrieval + structured metadata to create context‑rich retrieval for RAG and agentic AI solutions.

Skill Requirements

• Document Intelligence & NLPHands‑on experience building document ingestion, parsing, OCR, chunking, metadata extraction, classification, entity extraction and semantic enrichment pipelines.
• Apache Iceberg Vector Store & SearchStrong experience using Apache Iceberg as the governed storage layer for document chunks, metadata and vector embeddings, with vector similarity search, indexing, filtering and retrieval over Iceberg‑backed data. Current implementations can store embeddings in Iceberg tables and perform similarity search through vector‑capable query engines, with indexes used to accelerate retrieval.
• Vector & Retrieval EngineeringExperience with embedding generation, vector indexing, similarity search, ANN concepts, metadata filtering, hybrid search, reranking and retrieval‑quality evaluation for enterprise‑scale RAG.
• Apache Ossie Semantic LayerExperience with Apache Ossie for vendor‑neutral semantic models covering datasets, fields, relationships, metrics and AI context, providing consistent business meaning to analytics and AI applications.
• Knowledge Graph & Graph QueryingExperience designing knowledge graphs and modelling relationships between documents, entities and business concepts, including GQL/Cypher or equivalent graph‑query approaches.
• NetworkX & Graph AnalyticsStrong Python and NetworkX experience for graph construction, traversal, relationship analysis, centrality, community detection and other graph algorithms.
• Hybrid Knowledge Retrieval / RAGExperience combining Iceberg vector search + semantic models + graph retrieval + structured metadata to create context‑rich retrieval for RAG and agentic AI solutions.

Other Requirements