1 to 25 of 84 Permanent Semantic Search Jobs in the UK

## Director, Search & AI EvaluationApplylocations: London: Amsterdamtime type: Full timeposted on: Posted Todayjob requisition id: R113861**D****irector,** **Search & AI evaluation****Ready to lead a data science organisation that pushes the boundaries of what intelligent systems can achieve? Do you thrive on shaping strategy, inspiring teams, and delivering … mission is to help researchers, clinicians, and life sciences professionals advance discovery and improve health outcomes through trusted content, data, and analytics. Our Search & Evaluation organization plays a critical role in shaping the future of AI-powered discovery by building intelligent retrieval, ranking, and evaluation systems that power trusted ...

multinational institutions. Задачи: Own and evolve Corestream, Kharon's risk intelligence feed for entity-level insights and topic-based risk narratives; Redesign and improve semantic search capabilities using BM25 tuning, semantic distance, RAG, and reranking; Integrate Kharon's risk analysis outputs into the search layer … graph-based insights surface meaningfully in search results and sub-network exploration; Drive the evolution of the narrative generation pipeline that transforms graph and analytical data into accurate written intelligence for customers; Partner with Product and Engineering to own the Corestream roadmap and advance it; Optimize the metrics defining ...

enabling business information to be effectively discovered, understood and consumed by AI agents. The role sits at the intersection of data science, information retrieval, semantic search and AI, with a focus on improving how enterprise knowledge is represented, retrieved and evaluated. Key Responsibilities ● Design and optimise enterprise knowledge … retrieval capabilities. ● Develop and improve taxonomy and semantic models to support enterprise search. ● Apply metadata enrichment techniques to improve knowledge discovery. ● Develop and optimise semantic retrieval and search relevance. ● Work with embedding models and other AI techniques to improve information retrieval. ● Apply query understanding and prompt engineering ...

risk intelligence feed — a dynamic platform that surfaces entity-level insights and topic-based risk narratives to customers Redesigning and improving Kharon's semantic search capabilities, opening new avenues for content discovery — drawing on modern approaches including BM25 tuning, semantic distance, RAG, and reranking Integrating Kharon … risk analysis outputs into the search layer, ensuring that graph-based insights surface meaningfully within search results and sub-network exploration Driving the evolution of Kharon's narrative generation pipeline — how we take graph and analytical data and transform it into compelling, accurate written intelligence for customers Partnering ...

Agentic AI solutions Develop AI Agents and Multi-Agent Systems Work with LangChain, LangGraph and MCP Build intelligent retrieval using Embeddings, Vector Databases and Semantic Search Apply Prompt & Context Engineering Integrate AI solutions through REST APIs and cloud platforms Test, evaluate and optimise LLM and AI Agent performance … enterprise environments Cloud experience across Azure, AWS or GCP Understanding of LLM evaluation and testing Nice to have: Enterprise Knowledge Base/AI Search experience Knowledge Graphs Semantic Search Responsible AI AI Evals Token optimisation/cost management Financial Services experience Deadline for applications is Tuesday ...

Operating Model programme for a central government department. Where the Lead Technical Architect sets direction, you turn it into working, production-grade systems - semantic search, RAG pipelines, and broader generative AI capability - integrated into complex Legacy and multi-cloud environments handling high-volume, sensitive public sector data. … direct hands-on depth across the AI engineering stack is essential: - Strong general-purpose programming (most commonly Python) applied to AI/ML systems - Semantic search, vector/embedding infrastructure, and RAG pipeline construction - LLM orchestration and agentic frameworks (eg LangChain/LlamaIndex-style tooling, multi-agent patterns ...

build systems across: Large language models and multi-model architectures Natural language processing and information extraction Agentic and automated research workflows Retrieval, embeddings and semantic search Narrative detection and clustering Multilingual text intelligence Large-scale data and model pipelines Model evaluation, observability and monitoring Production ML infrastructure … reached real users. Worked with transformer architectures or fine-tuned language models. Designed evaluation frameworks for generative AI systems. Built retrieval, RAG, embedding or semantic-search systems. Worked with large, noisy or multilingual text datasets. Built high-throughput or low-latency data pipelines. Experience operating machine learning models ...

Design, build, integrate, deploy, and operate production AI/ML and LLM-based services for legal research, analytics, and content use cases. Implement RAG, semantic search, embeddings‐based retrieval, ranking, summarisation, classification, content enrichment, and citation‐aware AI capabilities where appropriate. Design and implement agentic workflows, tool orchestration … model lifecycle management, CI/CD, testing, monitoring, release management, observability, and operational support. Practical experience with LLM‐based capabilities, including retrieval‐augmented generation, semantic search, embeddings, prompt design, evaluation, guardrails, and observability. Experience with agentic workflows, tool orchestration, and multi‐step AI processes. Strong AWS knowledge, including ...

Design, build, integrate, deploy, and operate production AI/ML and LLM-based services for legal research, analytics, and content use cases. Implement RAG, semantic search, embeddings-based retrieval, ranking, summarisation, classification, content enrichment, and citation-aware AI capabilities where appropriate. Design and implement agentic workflows, tool orchestration … model lifecycle management, CI/CD, testing, monitoring, release management, observability, and operational support. Practical experience with LLM-based capabilities, including retrieval-augmented generation, semantic search, embeddings, prompt design, evaluation, guardrails, and observability. Experience with agentic workflows, tool orchestration, and multi-step AI processes. Strong AWS knowledge, including ...

Design, build, integrate, deploy, and operate production AI/ML and LLM-based services for legal research, analytics, and content use cases. Implement RAG, semantic search, embeddings-based retrieval, ranking, summarisation, classification, content enrichment, and citation-aware AI capabilities where appropriate. Design and implement agentic workflows, tool orchestration … model lifecycle management, CI/CD, testing, monitoring, release management, observability, and operational support. Practical experience with LLM-based capabilities, including retrieval-augmented generation, semantic search, embeddings, prompt design, evaluation, guardrails, and observability. Experience with agentic workflows, tool orchestration, and multi-step AI processes. Strong AWS knowledge, including ...

data pipelines for structured and unstructured data used in AI application workflows Support the implementation of retrieval-based and prompt-driven AI experiences, including semantic search and contextual response generation Optimize application and model integration performance for scalability, reliability, latency, and maintainability Collaborate with cross-functional teams … optimization, and scalable backend architectures Experience with unit testing, debugging, version control, and software engineering best practices Familiarity with data processing, prompt-driven workflows, semantic search, or retrieval‐based AI patterns is a strong plus Ability to work effectively in a collaborative team environment with strong problem‐solving ...

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 ...

development, testing, code review, documentation, and operational support. Help embed responsible AI capabilities into product workflows and platform services, including intelligent assistants, workflow automation, semantic search, knowledge retrieval, and reasoning over compliance and investment information. Build scalable, resilient, and operable systems that balance functional requirements with non-functional … designing and operating APIs, microservices, distributed systems, and event-driven architectures at enterprise scale. Exposure to Generative AI, large language models, retrieval-augmented generation, semantic search, embeddings, knowledge retrieval, or agentic workflow patterns. Strong focus on software quality, including automated testing, TDD, BDD, code review discipline, observability, resiliency ...

Engineering, and will share in the ownership and delivery of cutting edge, scalable ML models. Initial workstreams will likely include: Content Recommendation and Personalisation Search Optimisation Audio Modelling You will play a crucial role in transforming our data into genuinely useful product features that empower artists and connect … Data Scientist, you will be responsible for: Developing and implementing ML-based solutions to enhance and optimise the Beatport customer experience. This may include semantic search to improve crate digging, content recommendation/personalisation engines, or leveraging our catalog for the development of best-in-class audio models ...

Intelligence Engineering and will share in the ownership and delivery of cutting‐edge, scalable ML/AI models. Initial Workstreams Recommendations and personalization Search optimization Audio modeling As a Senior ML & AI Engineer, you will be responsible for: Developing and implementing ML and AI based solutions to enhance … optimize the Beatport customer experience, including semantic search, content recommendation/personalization engines, and audio models for music professionals. Acting as a subject matter expert regarding GCP’s latest ML/AI tooling and continuously prototyping and advocating for new tooling. Owning the development cycle ...

build, fine-tune and evaluate production NLP and language models across customer feedback intelligence products. You'll work on problems spanning sentiment analysis, retrieval, search, clustering, taxonomy generation and GenAI-powered insight generation while owning model performance from experimentation through deployment. Key Responsibilities Train, fine-tune and optimise transformer … models, LLMs and SLMs for production use cases Design and execute rigorous evaluation frameworks, experiments and benchmarking processes Build and improve semantic search, retrieval and reranking systems Develop solutions across aspect-based sentiment analysis, classification and taxonomy generation Partner closely with Product and Engineering teams to ship production ...

arrangement, with compensation ranging from £90,000 to £105,000 annually. The successful candidate will own and evolve Kharon's risk intelligence platform, redesign semantic search capabilities, and partner with product and engineering teams. The role requires a strong background in data science, familiarity with semantic search ...

communicate research findings effectively to both technical and non-technical audiences. Experience in one or more of the following would be advantageous: Researching AI, semantic search, search or data products. Working with emerging technology. Complex digital transformation programmes. Central government or wider public-sector environments. Working within ...

confidence. To learn more about Comply, visit comply.com The Role We are looking for Senior AI Data Engineers to implement and operationalize Comply’s semantic layer — turning the ontological models defined by our ontologist and architects into working knowledge graphs, vector search infrastructure, and LLM‐powered pipelines. This … hands‐on engineering role at the intersection of knowledge representation, AI infrastructure, and data platform engineering. You will own the delivery of semantic layer components, collaborate closely with application and data engineering teams, and ensure that AI‐ready data products are reliable, performant, and adopted in practice. You will ...

Multi-agent systems Tool calling Function orchestration Workflow automation Planning and reasoning patterns Human-in-the-loop design Knowledge & Retrieval RAG architectures Vector databases Semantic search Enterprise search Document ingestion Knowledge graphs (advantageous) Integration APIs Event-driven architectures Microsoft ecosystem ServiceNow CRM/ERP integration Identity management ...

equivalent orchestration framework, plus the judgement to know when to use none of them. RAG and retrieval: Chunking strategy, embeddings, hybrid and semantic search, re‐ranking, citation and provenance, natural‐language‐to‐query translation. Data platforms: NoSQL databases such as MongoDB (aggregation pipelines, Atlas Search, Atlas Vector … Search) or a strong equivalent, plus SQL. Comfortable designing schemas for agent retrieval, not just for OLTP. Data engineering: Building ingestion and enrichment pipelines over messy structured and unstructured sources, documents, PDFs, object storage. Evaluation: Building eval harnesses and eval datasets, LLM‐as‐judge with its limits understood, regression ...

frameworks such as PyTorch, TensorFlow, and Keras. Develop Retrieval-Augmented Generation (RAG) applications using LangChain, Hugging Face, and LlamaIndex. Implement and optimize vector database, semantic search, and hybrid search solutions for AI-powered applications. Perform model fine-tuning using advanced techniques such as LoRA and QLoRA … repositories Proficiency in LangChain and LlamaIndex for building AI-powered workflows Experience implementing Retrieval-Augmented Generation (RAG) frameworks Knowledge of Vector Databases and Hybrid Search techniques Strong understanding of Natural Language Processing (NLP) concepts and applications Experience with data processing, transformation, and feature engineering Expertise in developing and integrating ...

organization develops foundational AI technologies that power experiences such as LeapSpace , Elsevier’s AI-powered research assistant, as well as Elsevier’s broader Search & AI Platform . The Platform Data Science organization works at the intersection of: Search and retrieval systems Generative AI and LLM applications AI evaluation … experimentation Semantic enrichment and knowledge systems Scalable AI platforms and intelligent workflows About the role We are looking for a Data Scientist III to help design, build, and evaluate advanced AI capabilities supporting LeapSpace and Elsevier’s Search & AI Platform initiatives. This role focuses on applied AI development ...

probability, optimization, experimentation, and applied machine learning**.* Advanced proficiency in Python and modern AI frameworks, including **PyTorch, TensorFlow, Scikit-Learn, Hugging Face, LangChain, Semantic Kernel, and related ecosystems**.* Experience building and scaling **enterprise AI platforms, ML infrastructure, and intelligent applications serving thousands of users**.* Strong understanding … frameworks, experimentation, reliability, and operational perfection**.* Expertise in cloud-native AI development using **Azure AI Foundry, Azure Machine Learning, Azure OpenAI, Azure AI Search, AWS AI Services, and modern cloud architectures**.* Experience implementing **MLOps and LLMOps practices**, including CI/CD, model lifecycle management, governance, and production ...

libraries such as Transformers, LangChain, scikit-learn, PyTorch, or TensorFlow. Experience with OpenAI (GPT-4), Claude, Mistral, LLaMA, or similar models. Knowledge of vector search, embedding models (e.g., BERT, Sentence Transformers), and semantic search techniques. Ability to build scalable AI workflows and deploy them via APIs ...