Elasticsearch Engineer (Enterprise Search,AI Search,RAG) UN-client | 3 months initial | Fully Remote

Elasticsearch Engineer (Enterprise Search, AI Search, RAG) - UN Agency client (3 months initial, extensions likely) | Fully Remote

• For our world-famous UN agency client we are looking for an experienced Elasticsearch Engineer to join the AI Search product development team.
• Experience building production-grade Enterprise Search platforms based on Elasticsearch/OpenSearch, including hybrid search, semantic search, vector search and Retrieval-Augmented Generation (RAG), is highly desirable.
• This is primarily an Enterprise Search engineering role. General AI/LLM experience without strong hands-on Elasticsearch experience is unlikely to be sufficient.

• Location: Rome/Fully Remote (hybrid possible)
• Start: September 2026
• Duration: 3 months initial, extensions likely

Background

The consultant will design, build and maintain the data ingestion, processing, indexing and Retrieval-Augmented Generation (RAG) pipelines for a new Enterprise Search platform. The solution combines secure document ingestion, Elasticsearch/OpenSearch, hybrid search, semantic search, vector search and Large Language Models (LLMs) to deliver accurate, contextual and traceable answers.

Key Responsibilities & Deliverables
1. Enterprise Search & Data Engineering

• Design and implement scalable ingestion pipelines and connectors for SharePoint, Liferay, Azure Data Lake, databases and web content
• Develop batch, incremental and near-Real Time indexing
• Design Elasticsearch mappings, analyzers and indexing strategies
• Implement semantic chunking, metadata extraction, enrichment and deduplication
• Convert enterprise documents (PDF, Word, Excel, PowerPoint, HTML, scanned documents) into structured Markdown/embeddings

2. Build Retrieval Capabilities

• Develop hybrid Enterprise Search combining keyword search, semantic/vector search, metadata filtering and re-ranking
• Implement query rewriting, query expansion, metadata-aware retrieval, parent-child retrieval and contextual retrieval
• Ensure permission-aware and secure retrieval

3. Build RAG Pipelines

• Design and implement production-grade Retrieval-Augmented Generation pipelines
• Develop agentic workflows with tool/function calling and multi-step reasoning
• Implement prompt engineering, guardrails, context assembly and fallback strategies
• Build secure APIs (FastAPI) for ingestion, search and RAG orchestration

Required Profile & Experience

• Deep hands-on Elasticsearch/OpenSearch experience (Query DSL, mappings, analyzers, BM25, relevance optimisation, hybrid search)
• Strong Python development skills
• Experience with Elasticsearch, OpenSearch or Azure AI Search
• Experience with Enterprise Search, AI Search, semantic search, vector search and RAG architectures
• Practical knowledge of LangChain, LlamaIndex, Haystack or similar frameworks
• Experience with embedding models, re-ranking and LLM orchestration (OpenAI, Azure OpenAI, Anthropic, Gemini, Llama, Mistral, etc.)
• Experience with FastAPI and production-grade enterprise AI applications
• Experience with Marker, Docling or similar document-conversion frameworks is an advantage
• Excellent English (written and spoken)

Requirements

• Minimum 5 years professional experience, including at least 3 years building Enterprise Search, AI Search, semantic search, RAG or LLM-based applications
• Experience with production-grade Enterprise Search solutions
• Strong problem-solving and communication skills in an international environment

Advice to improve your chances: Our UN client will evaluate candidates primarily based on the technologies and responsibilities explicitly described in the CV. Candidates should clearly describe their hands-on experience with:

• Elasticsearch/OpenSearch
• Query DSL, BM25, mappings and analyzers
• Enterprise Search/AI Search
• Hybrid Search/Vector Search
• RAG implementations
• Embeddings and re-ranking
• LangChain/LlamaIndex/Haystack
• Agentic AI/Tool Calling
• FastAPI
• LLM integrations
• Document chunking
• Marker/Docling

Listing only project names or job titles is not sufficient.

AWARD & OTHERS

• The applicant's attention is drawn to the important role that the curriculum vitae plays in the evaluation.
• Curriculum vitae shall illustrate the specific skills relevant to this request.
• We would like to receive CVs of suitable candidates together with pricing quotations based on a daily net rate.
• Please apply only if you are available on short notice and full-time.
• Please note that I do not work with agencies or consulting companies. Direct applications only.

PROVIDER

infom consulting is an owner-managed business and consulting firm in Germany. The company supports large corporations and larger SMEs across Europe. Our IT experts are realising projects for the European Institutions, United Nations agencies, International Organisations and multinational companies across the EU.

TO APPLY. Please send:

1. A 3-4 sentence introduction summarising how your experience matches this specific role
2. Your all-inclusive daily rate in EUR (remote and onsite if applicable)
3. Your CV in DOC format highlighting your actual Enterprise Search, Elasticsearch, RAG and AI Search experience
4. Examples of projects where you personally designed or built Enterprise Search or RAG solutions
5. Availability/notice period