ENTERPRISE SEARCH ENGINEER

Under the guidance of the ICT Solutions Coordinator, the Enterprise Search Engineer will collaborate closely with ICT teams to deliver a robust and intelligent search platform. This role involves designing and implementing data ingestion pipelines, building hybrid search capabilities, and creating RAG pipelines for accurate and relevant content retrieval and generation. The engineer will also be responsible for ensuring the platforms performance, scalability, and security, as well as contributing to the overall success of the project through effective problem-solving, teamwork, and organization skills.

• Proven hands-on experience with Elasticsearch, including query DSL, BM25 tuning, and multi-field matching strategies.
• Ability to design mappings, choose field types, and configure custom analyzers for different content types.
• Real-world experience building connectors and ingestion pipelines for SharePoint, Liferay, databases, and Azure Data Lake.
• Deep understanding of hybrid and semantic search techniques, including lexical and vector search.
• Proficiency in Python and data processing frameworks/libraries for data engineering tasks.
• Experience with embedding models, re-ranking models, and prompt engineering for reliable response generation.
• Knowledge of LLM orchestration frameworks like LangChain, LlamaIndex, or Haystack for AI application orchestration.
• Familiarity with tool calling, agentic workflows, and multi-step retrieval for complex AI tasks.
• First-level University degree in Computer Science, Engineering, or related field with 5+ years of professional experience.
• Excellent written and verbal communication skills in English, with the ability to collaborate effectively in a multicultural setting.

• Design and implement data ingestion pipelines for structured, semi-structured, and unstructured content from various enterprise sources.
• Develop hybrid search capabilities combining keyword and semantic vector search with metadata filtering and contextual retrieval.
• Build RAG pipelines to retrieve relevant enterprise content and generate grounded answers using large language models.
• Implement semantic chunking strategies to improve retrieval accuracy in RAG applications.
• Design ingestion pipelines to convert enterprise documents into structured Markdown, preserving layout and metadata.
• Ensure the search index is accurate and current by tracking document versions, access permissions, and deletion events.
• Implement advanced retrieval techniques, security controls, and re-ranking pipelines to enhance relevance and user access.
• Collaborate with ICT teams to deliver a well-engineered and functioning enterprise search solution.
• Stay updated with the latest technologies and trends in enterprise search, AI, and large language models.