> Markdown version of [/jobs/ext/2258416-ai-nlp-engineer](https://www.wearedevelopers.com/jobs/ext/2258416-ai-nlp-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI NLP Engineer - **Company:** Xantura Limited - **Location:** Greater London, UK (Remote available) - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Apache HTTP Server, Automated Storage and Retrieval Systems, Microsoft Azure, Cloud Storage, Encodings, Computational Linguistics, Computer Programming, Graph Database, Information Extraction, Information Retrieval, Python (Programming Language), Key Management, Machine Learning, Neo4j, Named Entity Recognition, Performance Tuning, Search Technologies, Semantic Web, SPARQL, Cloud Monitoring, Large Language Models, Multi-Agent Systems, Prompt Engineering, Generative AI, Backend, Information Technology, Azure AKS, Virtual Agents, Text Analysis, Document Classification, Data Pipelines - **Published:** August 26, 2026 - **Apply:** https://www.collegerecruiter.com/job/2815142865-ai-nlp-engineer ## About the Role * Bachelor's or Master's degree in Computer Science, Computational Linguistics, Machine Learning, or a related technical field, or equivalent practical experience. * 3+ years of professional experience in an NLP, ML, or AI engineering role. * Strong programming skills and production experience in Python. Clear evidence of practical experience across some or all of the following * LLM utilisation in production; prompt engineering, output structuring, chaining, and integrating LLMs into data processing pipelines (e.g. via LangChain, PydanticAI, or similar). * Embedding models; training, fine-tuning, or serving embedding models (e.g. sentence-transformers, bi-encoders, cross-encoders), with practical experience setting up and managing vector databases (e.g. Qdrant, Weaviate, Milvus, pgvector) along with understanding trade-offs e.g. when to use sparse or dense embeddings (or both) etc. * Classical NLP training and evaluating text classifiers, NER models, or other supervised/semi-supervised NLP models for domain-specific tasks., * Experience with knowledge graphs/triplestores/semantic web frameworks (e.g. Neo4j, RDF/SPARQL/OWL, Apache Jena). * Practical experience with entity linking, concept normalisation, or ontology-driven NLP. * Experience with retrieval-augmented generation (RAG) pipelines. * Familiarity with agentic AI frameworks and multi-agent orchestration (e.g. LangGraph, AutoGen). * Good familiarity with the Azure ecosystem (Azure Kubernetes Service, Azure Container Registry, Azure DevOps, Azure Blob Storage, Azure Monitor, Azure Key Vault). This is a hybrid role based in our office in London (Borough). You would be expected to be able to work from the office at least 1-2 days per week. Some travel is required for on-site client engagements as needed. ## Description AI NLP Engineer Department: Platform Delivery Employment Type: Permanent - Full Time Location: London Description In this role you will work in the Platform team - a function for the deployment and evolution of the backend platform that underpins the core of the Xantura business. The Role You'll own and evolve Xantura's text analytics platform (XTA), the NLP system that extracts structured intelligence from unstructured case notes across health, housing, and social care. You'll work across the full spectrum of NLP: from classical text classification and entity extraction through to LLM-based information extraction, embedding models, and retrieval systems. As the platform matures, you'll help shape our agentic AI capabilities. Key Responsibilities * Own and evolve the core text analytics pipeline; advancing large-scale concept extraction, classification, and information retrieval across complex social and clinical text corpora. * Design and implement LLM-based processing chains for structured information extraction, leveraging prompt engineering, output parsing, and model orchestration to produce high-quality, auditable outputs at scale. * Build and manage embedding infrastructure; training, fine-tuning, and serving embedding models, and setting up and operating vector databases to enable semantic search and retrieval across client data. * Develop and maintain classical NLP components where appropriate; training smaller classifiers, entity recognisers, and domain-specific models for tasks where efficiency and interpretability outweigh generative approaches. * Lay the groundwork for agentic AI capabilities as the platform evolves; contributing to the design of multi-agent orchestration, tool integration, and conversational interfaces over Xantura's services. * Ensure all NLP systems are robust, explainable, and aligned with Responsible AI principles; essential where outputs inform decisions about vulnerable people in health and social care. Skills, Knowledge & Expertise * Bachelor's or Master's degree in Computer Science, Computational Linguistics, Machine Learning, or a related technical field, or equivalent practical experience. * 3+ years of professional experience in an NLP, ML, or AI engineering role. * Strong programming skills and production experience in Python. Clear evidence of practical experience across some or all of the following * LLM utilisation in production; prompt engineering, output structuring, chaining, and integrating LLMs into data processing pipelines (e.g. via LangChain, PydanticAI, or similar). * Embedding models; training, fine-tuning, or serving embedding models (e.g. sentence-transformers, bi-encoders, cross-encoders), with practical experience setting up and managing vector databases (e.g. Qdrant, Weaviate, Milvus, pgvector) along with understanding trade-offs e.g. when to use sparse or dense embeddings (or both) etc. * Classical NLP training and evaluating text classifiers, NER models, or other supervised/semi-supervised NLP models for domain-specific tasks. Additional advantages * Experience with knowledge graphs/triplestores/semantic web frameworks (e.g. Neo4j, RDF/SPARQL/OWL, Apache Jena). * Practical experience with entity linking, concept normalisation, or ontology-driven NLP. * Experience with retrieval-augmented generation (RAG) pipelines. * Familiarity with agentic AI frameworks and multi-agent orchestration (e.g. LangGraph, AutoGen). * Good familiarity with the Azure ecosystem (Azure Kubernetes Service, Azure Container Registry, Azure DevOps, Azure Blob Storage, Azure Monitor, Azure Key Vault). This is a hybrid role based in our office in London (Borough). You would be expected to be able to work from the office at least 1-2 days per week. Some travel is required for on-site client engagements as needed. Job Benefits * Competitive salary reviewed annually * Work for a passionate, mission-driven company solving society's big problems * Work flexible hours around life commitments with a focus on delivering company value rather than hours worked * Ability to work remotely (excluding face-to-face Team Meetings and client meetings) * Training and development opportunities * 25 days annual leave (plus bank holidays) * Company pension * Private medical insurance * Generous enhanced parental leave policies * Cycle to work scheme * Flu Vaccinations * Eye Test and contribution towards Glasses for VDU use Employee Assistance Programme * Mental health and wellbeing support * Remote GP access * Counselling/therapy * Physiotherapy * Medical second opinions ## Related Videos - [Agentic AI - From Theory to Practice: Developing Multi-Agent AI Systems on Azure](https://www.wearedevelopers.com/videos/1532-agentic-ai-from-theory-to-practice-developing-multi-agent-ai-systems-on-azure) - [Developing the Backend with Stefan Lingler, CTO at Shpock](https://www.wearedevelopers.com/videos/100360-developing-the-backend-with-stefan-lingler-cto-at-shpock) - [Putting the Graph In GraphQL With The Neo4j GraphQL Library](https://www.wearedevelopers.com/videos/257-putting-the-graph-in-graphql-with-the-neo4j-graphql-library) - [Coffee with Developers - Maria Apazoglou](https://www.wearedevelopers.com/videos/1209-coffee-with-developers-maria-apazoglou) - [Nest.js - TypeScript in the backend can also be clean](https://www.wearedevelopers.com/videos/1033-nest-js-typescript-in-the-backend-can-also-be-clean) - [Cyber Sleuth: Finding Hidden Connections in Cyber Data](https://www.wearedevelopers.com/videos/893-cyber-sleuth-finding-hidden-connections-in-cyber-data) ## Related Articles - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [What Are Large Language Models?](https://www.wearedevelopers.com/magazine/304-what-are-large-language-models) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [Coffee with Developers - Maria Apazoglou - Making AI understandable for all in production](https://www.wearedevelopers.com/magazine/475-coffee-with-developers-maria-apazoglou-making-ai-understandable-for-all-in-production) - [Graph and AI Trends 2026: Why Is AI Running but Not Yet Delivering?](https://www.wearedevelopers.com/magazine/680-graph-and-ai-trends-2026-why-is-ai-running-but-not-yet-delivering) - [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline)