Data & AI Engineer (Contract) - NLP, Vector Search, Graphs

ALOIS UK; Perth; On-site; AUD 165,000 - 248,000; Full time

Job summary

ALOIS Australia is seeking a Data & AI specialist for a contract assignment in Melbourne. You will lead end-to-end document intelligence initiatives, building ingestion, NLP, and vector-based retrieval pipelines. You will work with Iceberg-backed storage, vector search, and semantic models, designing knowledge graphs and graph queries.

Strong Python and NetworkX skills are required. The role focuses on hybrid retrieval, RAG solutions, and enterprise-scale data analytics to empower AI-driven

Qualifications

• Hands-on experience building document ingestion, OCR, metadata extraction pipelines.
• Experience with Iceberg-backed vector search and retrieval.
• Experience with vector embeddings, indexing, and similarity search.
• Experience with semantic models and knowledge graphs.
• Proficient in Python and graph analytics using NetworkX.
• Hybrid retrieval/RAG for enterprise AI solutions.

Responsibilities

• Build document ingestion, OCR, chunking, and extraction pipelines.
• Implement Iceberg vector store for metadata and embeddings.
• Develop vector indexing and similarity search for retrieval.
• Work with Apache Ossie semantic layer for data context.
• Design knowledge graphs and queries with GQL/Cypher.
• Apply Python and NetworkX for graph analytics.
• Create hybrid retrieval solutions for RAG/AI agents.

Skills

Document Intelligence

Vector Retrieval

Knowledge Graph

Graph Analytics

Hybrid Retrieval

NLP/Pipeline Development

Python

Tools

Apache Iceberg

Apache Ossie

GQL/Cypher

NetworkX

Job description

ALOIS Australia is seeking a Data & AI specialist for a contract assignment in Melbourne. You will lead end-to-end document intelligence initiatives, building ingestion, NLP, and vector-based retrieval pipelines. You will work with Iceberg-backed storage, vector search, and semantic models, designing knowledge graphs and graph queries.

Strong Python and NetworkX skills are required. The role focuses on hybrid retrieval, RAG solutions, and enterprise-scale data analytics to empower AI-driven