AI/Data Engineer (RAG, LLM, Elasticsearch) UN Agency-client (4 months initial, extensions likely, immediate start) | Fully Remote

For a large UN agency client we are looking for an experienced AI/Data Engineer to join the AI Search product development team.

• Location: Rome/Fully Remote (hybrid possible)
• Start: Immediate
• Duration: 4 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 AI Search platform. The solution combines secure document ingestion, vector search, semantic search and Large Language Models (LLMs) to deliver accurate, contextual and traceable answers to users.

Key Responsibilities & Deliverables:

1. Data Engineering
Design and implement scalable data ingestion pipelines from various enterprise sources (SharePoint, Liferay, web crawls, etc.)
Develop connectors supporting batch, incremental and near-Real Time indexing
Implement semantic chunking strategies, metadata extraction, enrichment and deduplication
Convert complex documents (PDF, Word, Excel, PowerPoint, HTML, scanned docs, etc.) into clean Markdown for optimal AI processing

2. Build Retrieval Capabilities
Develop hybrid search (keyword + semantic vector search) with metadata filtering
Implement re-ranking pipelines and advanced retrieval techniques (query rewriting, multi-query, parent-child, contextual compression)
Ensure secure, permission-aware retrieval

3. Build RAG Pipelines
Design and implement full Retrieval-Augmented Generation pipelines
Develop agentic workflows with tool calling and multi-step reasoning
Implement prompt engineering, guardrails, context assembly and fallback strategies
Build secure and scalable APIs (FastAPI) for ingestion, search and RAG orchestration

Required Profile & Experience:

• Strong Python development skills
• Hands-on experience with Elasticsearch/OpenSearch/Azure AI Search
• Solid experience with vector search, semantic 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 building production-grade enterprise AI applications
• Excellent English (written and spoken)

Requirements:

• Minimum 5 years professional experience, of which at least 3 years hands-on building AI Search, RAG or LLM-based applications
• Experience with production-grade solutions (observability, security, CI/CD)
• Strong problem-solving and communication skills in a multicultural environment

AWARD & OTHERS

• The applicants 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 when you are available immediately or on short notice (and Full-time).
• Please respect, that I am NOT working with agencies/companies.

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 DO - QUESTIONS, to apply, please send:

1. 3-4 sentence introduction summarising how your experience matches the role
2. All-inclusive daily rate in EUR (remote + onsite if applicable)
3. CV in DOC format highlighting relevant RAG, vector search and LLM experience
4. Details of projects where you personally designed/built RAG or AI Search solutions
5. Availability/notice period