Elastic Search Consultant

About the role

You will work closely with ICT teams to design, build and optimize an enterprise search platform powered by Elasticsearch and modern AI technologies. The role spans the full search lifecycle, from data ingestion and indexing through to semantic retrieval, relevance optimization and RAG orchestration.

This position requires a strong combination of search engineering, data engineering, AI integration and platform design expertise. You will be responsible for ensuring that enterprise content is searchable, relevant, secure and optimized for AI-assisted experiences.

Data Engineering & Content Ingestion

• Design and implement scalable ingestion pipelines for structured, semi-structured and unstructured content
• Build integrations with enterprise platforms including SharePoint, Liferay, Azure Data Lake, web sources and internal business systems
• Develop indexing processes supporting batch, incremental and near real-time updates
• Implement document lifecycle management including version tracking, provenance, update detection and deletions
• Build content extraction pipelines for PDFs, Office documents, emails, HTML and scanned content
• Convert enterprise content into structured formats optimized for retrieval and AI consumption
• Implement metadata extraction, enrichment and content deduplication processes
• Design semantic chunking strategies that preserve context, hierarchy and document relationships

Search & Retrieval Engineering

• Design and implement hybrid search combining keyword, vector and metadata-driven retrieval
• Develop relevance ranking and re-ranking pipelines using embeddings and advanced retrieval models
• Implement query expansion, query rewriting and contextual retrieval strategies
• Optimize retrieval quality through semantic indexing and vector search architectures
• Develop parent-child retrieval models and contextual compression techniques
• Ensure access controls and security trimming are enforced within search results

AI & RAG Development

• Design and implement Retrieval-Augmented Generation pipelines
• Integrate enterprise search with Large Language Models and AI services
• Build agentic workflows capable of tool calling, API interaction and multi-step reasoning
• Design prompt orchestration frameworks and context management systems
• Implement fallback and confidence-handling strategies for ambiguous or low-quality queries
• Optimize grounding, traceability and response quality across AI search experiences

Search Platform Optimization

• Design Elasticsearch mappings, analyzers, tokenizers and indexing strategies
• Optimize search relevance using BM25, boosting, scoring functions and query DSL techniques
• Manage scaling, performance tuning and cluster health across enterprise search environments
• Build search evaluation frameworks using relevance benchmarks, precision, recall and NDCG metrics
• Continuously improve retrieval quality and search effectiveness through testing and analysis

Experience

• 5+ years of professional experience in enterprise search, search engineering or AI applications
• 3+ years of hands-on experience developing enterprise search, semantic search or RAG solutions
• Experience delivering production-grade search applications at scale
• Degree in Computer Science, Information Systems, Computer Engineering or related field

Core Technical Skills

• Deep hands-on Elasticsearch expertise
• Strong understanding of Query DSL, BM25 tuning and relevance optimization
• Experience designing scalable index mappings and content models
• Experience implementing lexical, vector and hybrid retrieval systems
• Strong knowledge of search performance optimization and cluster operations
• Experience with Elasticsearch, OpenSearch, Azure AI Search or similar platforms
• Strong Python development skills

AI & Semantic Search

• Experience building RAG systems and AI-powered search applications
• Knowledge of embeddings, semantic search and vector retrieval
• Experience with cross-encoders, re-ranking models and relevance pipelines
• Experience with LangChain, LlamaIndex, Haystack or similar orchestration frameworks
• Experience implementing tool calling, multi-step retrieval and agentic AI workflows
• Familiarity with commercial or open-source LLMs including OpenAI, Azure OpenAI, Anthropic, Gemini, Llama, Mistral or similar

Data Ingestion & Processing

• Experience integrating SharePoint, Liferay, databases and data lake environments
• Experience with CDC/incremental synchronization architectures
• Experience converting enterprise documents into structured AI-ready formats
• Familiarity with tools such as Marker, Docling or equivalent document processing frameworks
• Strong understanding of semantic chunking and metadata preservation techniques

Nice to have

• Experience with React or modern front-end development frameworks
• Experience building enterprise knowledge management platforms
• Familiarity with Microsoft 365 ecosystems
• Knowledge of enterprise security, permissions and governance models

Working style / behaviours

• Strong problem-solver capable of explaining complex concepts clearly
• Collaborative team player who works effectively across technical and non-technical teams
• Organised and capable of managing multiple priorities
• Analytical mindset with a strong focus on relevance, performance and user experience
• Comfortable working in multicultural and globally distributed environments

Why join

• Opportunity to build a large-scale enterprise AI search platform
• Work with cutting-edge semantic search, RAG and LLM technologies
• High-impact role shaping knowledge discovery across a global organisation
• Exposure to complex enterprise content ecosystems and AI innovation
• International environment with potential contract extension

Location: Rome, Italy or Remote

Employment type: Contract

Day rate range: £400-£600 GBP per day