24 of 24 Permanent Semantic Search Jobs in the UK

vector databases and traditional data platforms. Model complex business domains to improve retrieval quality and contextual understanding. Design and optimise hybrid retrieval strategies using semantic search, keyword search, embeddings and knowledge graphs. Evaluate, integrate and extend best-of-breed tooling rather than building infrastructure unnecessarily. Measure, monitor … scalable knowledge systems for AI-powered applications. Strong understanding of domain modelling, ontology design and information architecture. Hands-on experience with hybrid retrieval techniques, semantic search, embeddings and vector databases. Experience building reliable data pipelines and integrating multiple data sources. Excellent judgement in selecting the right technologies ...

doing Designing AI and GenAI architecture strategies and roadmaps Building scalable AI/ML and Agentic AI platforms Working across LLMs, RAG, embeddings and semantic search Supporting AI deployment, governance and integration patterns Collaborating with engineering, data, DevOps and business teams Advising clients on AI platform capability … implementation strategy Environment Python LLMs, prompt engineering, fine-tuning, RAG LangChain, LangGraph, Agent frameworks Vector databases and semantic search MLOps and LLMOps AWS, Azure, GCP, Databricks Containerisation, Kubernetes and GPU infrastructure Requirements Experience designing enterprise AI or ML architectures Strong understanding of cloud and modern data platforms Exposure ...

capability without long-term reliance on external suppliers. Key Responsibilities Architectural Leadership & Integration Design and implement enterprise-grade AI platforms - including semantic search, Retrieval-Augmented Generation (RAG), and broader generative AI/agentic capabilities - integrating cleanly with the department's complex Legacy and multi-cloud environments. Responsible … DDaT competencies, given the scale of this programme, hands-on depth across the modern AI engineering stack is essential, not just RAG in isolation: Semantic search, vector/embedding infrastructure, and retrieval architecture design LLM orchestration and agentic frameworks (eg LangChain/LlamaIndex-style tooling, multi-agent patterns ...

data trust and certification framework, enabling users to assess dataset quality, ownership, observability, and SLAs with confidence. Embed AI‐driven discovery features such as semantic search, natural language query, and recommendations to improve data discoverability and reduce time to insight. Translate complex platform and business needs into … Expertise in metadata management and data discoverability, including lineage, certification, and data contracts. Experience building or integrating AI/ML‐powered platform capabilities (e.g., semantic search, recommendations, NLP interfaces). Strong ability to influence architecture and operating models without direct authority. Experience using data to measure platform adoption ...

supporting high-quality delivery across AI and automation work Design secure, scalable and governed AI solutions using Azure AI Foundry, Azure OpenAI, Azure AI Search, Copilot Studio, Microsoft 365, Power Platform and related Azure services Architect multi-model and agentic AI solutions that integrate with enterprise data, APIs, workflows … delivery teams through clear architectural direction Hands‐on experience designing and implementing enterprise AI solutions using Microsoft Azure AI Foundry, Azure OpenAI, Azure AI Search, Copilot Studio and related Azure services Experience designing multi-model AI architectures, including model selection, orchestration, evaluation, grounding, cost management and responsible ...

distillation of LLMs (e.g, GPT, Llama, Claude, Gemini), machine learning libraries (e.g. scikit‐learn, XGBoost). Experience with data storage for AI, vector databases, semantic search, and knowledge graphs. Contributions to open‐source AI projects or research publications. Familiarity with AI security, privacy, and compliance standards e.g. ISO42001. ...

APIs and LLM-based applications. Experience with Retrieval-Augmented Generation (RAG) architectures. Understanding of AI agents and agentic workflows. Experience building knowledge management or search platforms. Experience with vector databases and semantic search technologies. Exposure to data engineering and machine learning workflows. Experience taking AI solutions from ...

Databricks or similar technologies Experience architecting scalable AI and ML solutions across serverless, containerised or GPU enabled environments Experience with LLMs, prompt engineering, embeddings, semantic search and RAG patterns Exposure to vector databases and agent frameworks such as LangChain, LangGraph or similar technologies Understanding of MLOps, LLMOps ...

Databricks or similar technologies Experience architecting scalable AI and ML solutions across serverless, containerised or GPU enabled environments Experience with LLMs, prompt engineering, embeddings, semantic search and RAG patterns Exposure to vector databases and agent frameworks such as LangChain, LangGraph or similar technologies Understanding of MLOps, LLMOps ...

Databricks or similar technologies Experience architecting scalable AI and ML solutions across serverless, containerised or GPU enabled environments Experience with LLMs, prompt engineering, embeddings, semantic search and RAG patterns Exposure to vector databases and agent frameworks such as LangChain, LangGraph or similar technologies Understanding of MLOps, LLMOps ...

tested, deployed and version-controlled Proactively monitoring pipeline health, optimising performance, and managing infrastructure costs to ensure efficient scaling Applying strong data modelling, semantic consistency and metadata discipline so data is discoverable and usable by both humans and AI tools Partnering with function-specific AI engineers and analysts … with Cloud Build and GitHub for version control and CI/CD A working understanding of how to keep data AI-ready: strong modelling, semantic consistency, and metadata discipline that both humans and AI tools can rely on Comfortable working across the full data landscape that a growing ...

role: - Design AI and GenAI architecture strategies and roadmaps - Build scalable AI/ML and Agentic AI platforms - Work across LLMs, RAG, embeddings and semantic search - Support AI deployment, governance and integration patterns - Collaborate with engineering, data, DevOps and business teams - Advise clients on AI platform capability ...

GenAI architecture strategy and roadmap. Build scalable AI/ML and Agentic AI platforms spanning LLMs, retrieval-augmented generation (RAG), embeddings and semantic search. Lead on deployment, governance and integration patterns, advise clients on platform capability and implementation strategy, and partner with engineering, data, DevOps and business teams ...

GenAI architecture strategy and roadmap. Build scalable AI/ML and Agentic AI platforms spanning LLMs, retrieval-augmented generation (RAG), embeddings and semantic search. Lead on deployment, governance and integration patterns, advise clients on platform capability and implementation strategy, and partner with engineering, data, DevOps and business teams ...

with enterprise objectives. Build scalable AI/ML and Agentic AI platforms, working across large language models (LLMs), retrieval-augmented generation (RAG), embeddings, and semantic search. Support AI deployment, governance, and integration patterns, and advise clients on platform capability and implementation strategy. Collaborate closely with engineering, data, DevOps ...

experience building solutions using LLMs, machine learning or applied AI techniques to solve practical business problems. Experience with prompt engineering, retrieval augmented generation, semantic search, AI workflow orchestration or agent-based approaches. Experience working with business or domain data to ground, evaluate and improve AI outputs. Ability … subject matter experts to shape ideas into deliverable software. Desired Skills Experience working with Azure PaaS services, Azure AI Foundry, Azure OpenAI, Azure AI Search or Azure Machine Learning. Experience with .NET, SQL Server and cloud-native application development. Knowledge of Semantic Kernel or similar AI orchestration frameworks. ...

asset management. Job Responsibilities Design and implement agentic AI workflows that automate and streamline complex business processes. Design and apply advanced techniques such as semantic search, retrieval‐augmented generation (RAG), named entity recognition (NER), prompt engineering, and personalization for content extraction, search, question answering, reasoning, and recommendation. ...

engineering mindset: you can build reliable pipelines, not just notebooks. Solid applied NLP/ML experience on real-world text: embeddings, clustering, topic modeling, semantic search, classification; you understand failure modes and how to debug them. Comfortable at scale: distributed processing, large-scale storage-querying, and performance-cost ...

workflows that automate complex business processes and deploy models into production. You will collaborate with business stakeholders and technologists to apply advanced analytics, semantic search, RAG, NER, and prompt engineering to financial data, with emphasis on experimentation and reliability. The role requires strong programming skills in Python ...

equivalent practical experience. A deep, hands‐on understanding of retrieval systems, RAG, embeddings, vector indexing, and knowledge representation. Experience with knowledge representation, semantic search, or agentic systems. Proven proficiency in Python, including writing production-quality, testable, and maintainable code. Experience scaling or shipping products at high-growth startups. ...

prompt engineering, or RAG pipeline construction * Familiarity with REST-based AI APIs (OpenAI, Anthropic, Google Vertex AI, or equivalent). * Basic understanding of embeddings, semantic search, and token-based context management. * Comfortable reading Python code or notebooks (most AI libraries are Python-first); ability to translate patterns into ...

prompt engineering, or RAG pipeline construction * Familiarity with REST-based AI APIs (OpenAI, Anthropic, Google Vertex AI, or equivalent). * Basic understanding of embeddings, semantic search, and token-based context management. * Comfortable reading Python code or notebooks (most AI libraries are Python-first); ability to translate patterns into ...

mitigating hallucinations and output errors. Deploy and maintain RAG architecture and LLM pipelines within cloud environments. Optimise data-chunking and text embeddings for optimal semantic search across a large, specialist corpus. Track the competitive landscape and stay current with technological advancements in GenAI. Monitor and optimise agent ...

NLP PEOPLE is seeking a Machine Learning Engineer in London (Hybrid) with a focus on NLP and LLMs. You will enhance retrieval systems and shape technical direction. The ideal candidate will have 5+ years of ...