The Role
Own and evolve Xantura's text analytics platform: build NLP pipelines, LLM-based extraction and RAG, manage embedding models and vector DBs, maintain classical NLP components, and design agentic AI while ensuring explainability and Responsible AI for sensitive health and social care data.
Summary Generated by Built In
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.
In addition, the following would be an advantage:
- 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
About
At Xantura, we’re on a mission to reduce societal inequality by helping local authorities use data more effectively. Our AI-driven platform empowers frontline workers with the insights they need to prevent complex issues like homelessness or children being taken into care — before they happen. We make this possible by connecting siloed datasets, applying advanced machine learning to enrich the data, and using predictive analytics to identify those most at risk. Our platform then distills this into clear, actionable insights that help frontline staff intervene early and make a real difference. It’s an exciting time to join Xantura. We’re scaling quickly, bringing on new clients, strengthening our platform, and expanding into new areas. While we’re a technology company at heart, our true focus is on improving lives — and we’re looking for people who share that vision.
Skills Required
- Bachelor's or Master's degree in Computer Science, Computational Linguistics, Machine Learning, or related field (or equivalent experience)
- 3+ years professional experience in an NLP, ML, or AI engineering role
- Strong programming skills and production experience in Python
- Production experience with LLMs: prompt engineering, output structuring, chaining, and integrating LLMs into data pipelines (e.g., via LangChain, PydanticAI)
- Experience with embedding models: training, fine-tuning, or serving embeddings (e.g., sentence-transformers, bi-encoders, cross-encoders) and operating vector databases (Qdrant, Weaviate, Milvus, pgvector)
- Experience training and evaluating classical NLP models: text classifiers, NER, supervised/semi-supervised domain-specific models
- Experience with knowledge graphs/triplestores/semantic web frameworks (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)
- Familiarity with Azure ecosystem: AKS, ACR, Azure DevOps, Blob Storage, Monitor, Key Vault
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
Xantura is a technology company that provides data sharing and advanced analytics to the public sector, using AI and machine learning to help local authorities improve outcomes for vulnerable people and reduce societal inequality.
