Software Engineer – Natural Language Search and AI Integration at EMBL

Hinxton, United Kingdom

on-site · full_time · Visa sponsorship

Apply for this role at EMBL

Responsibilities:
- Design, develop, and deploy prototype services that enable natural-language queries (NLQ) across EBI metadata and selected specialized searches (sequence, chemical, etc.).
- Implement MCP-based endpoints to expose search capabilities to AI agents and enable agent-driven workflows.
- Build a central NLQ entry point that integrates metadata search, specialized modalities, multilingual support, and text summarization.
- Integrate with search platforms (Lucene/SOLR, Elasticsearch) and ensure interoperability, scalability, and sustainability.
- Engage the user community: organise workshops, run surveys and UX testing, and iterate on requirements with researchers and curators.
- Collaborate with EMBL-EBI teams and external partners to deliver production-ready prototypes and documentation.

Requirements:
- University degree in Computer Science, Bioinformatics, or a related discipline.
- Strong software development experience (Python, Java, or similar) and familiarity with search technologies (Lucene/SOLR, Elasticsearch).
- Knowledge or experience with NLP, LLMs, conversational AI frameworks, and metadata indexing/search design.
- Experience with or willingness to adopt AI agent standards such as the Model Context Protocol (MCP).
- Demonstrated ability to work with scientific communities, run UX testing, and translate user needs into technical solutions.
- Excellent communication and collaboration skills; interest in biological data resources is a plus.