51 to 75 of 137 Semantic Search Jobs in the UK

productionization of AI/ML models, including large language models and agentic systems, retrieval-augmented generation, document AI and structured extraction, embeddings and semantic search, tree-based and classical machine learning, time series forecasting, and mathematical optimization. Support agentic and LLM-based pipelines end-to-end: retrieval, extraction ...

machine learning models and artificial intelligence architectures across Ecofamilies. You will translate user behaviors, parenting journeys, and marketplace preferences into tailored, dynamic feed landscapes, semantic search algorithms, and predictive recommendation layers, ensuring ethical execution and deep alignment with UK privacy regulations. What You'll Do Core Responsibilities … build, and maintain production-ready machine learning engines that drive product, directory, and content personalization arrays for our UK community base. Natural Language Processing & Search: Implement large language model (LLM) fine-tuning processes and Retrieval-Augmented Generation (RAG) loops to enrich community forum semantic searches, automated content categorizations ...

/ML & GenAI solutions Strong Python & Java skills Experience with LangChain, LlamaIndex, CrewAI, or similar Knowledge of RAG, vector databases, and semantic search AWS cloud expertise (Bedrock, SageMaker preferred) Experience with APIs, microservices, and cloud-native architecture Nice to Have AWS certifications (ML/Architect) Experience with MLOps ...

challenges from first principles. Ability to commute to a London office once per week. Desirable Experience AI orchestration and workflow frameworks. Knowledge graph or semantic search technologies. Model fine-tuning and evaluation. MLOps, CI/CD, containerisation, and cloud-native deployment practices. Experience developing autonomous agents and reasoning ...

agent orchestration frameworks, workflow automation platforms, or tool‐augmented LLM applications Experience with context engineering techniques, including retrieval strategies, embeddings, vector databases, knowledge graphs, semantic search, memory management, and grounding approaches Experience building evaluation frameworks for AI applications, including golden datasets, automated scoring, human review workflows, red teaming ...

evaluation (eval datasets, automated and expert‐in‐the‐loop scoring, regression testing). Experience with API integration, retrieval layers, knowledge graphs, ontologies, or semantic search. Daily use of AI coding agents (Claude Code, GitHub Copilot, Databricks AI Assistant) as the primary mode of development. Preferred Experience Prior experience ...

evaluation (eval datasets, automated and expert-in-the-loop scoring, regression testing). Experience with API integration, retrieval layers, knowledge graphs, ontologies, or semantic search. Daily use of AI coding agents (Claude Code, GitHub Copilot, Databricks AI Assistant) as the primary mode of development. Preferred Experience Prior experience ...

production, including multi-agent orchestration, tool use via MCP, agent memory and agentic RAG.Depth in NLP, such as information extraction, classification, summarisation and semantic search, or fine-tuning LLMs. Experience building shared AI platforms or reusable capabilities consumed by multiple product teams, such as internal MCP servers … agent tooling. Experience with vector search at scale, using tools such as OpenSearch, Amazon S3 Vectors or pgvector. Familiarity with AI governance and regulation, and with putting responsible AI practices into day-to-day engineering. An advanced degree in computer science, data science, linguistics or a related quantitative field ...

Foundry, Azure OpenAI, Claude and open-source large language models, you'll design and deploy enterprise-scale AI products using agentic AI, RAG, vector search and machine learning technologies. You'll lead a blended team of AI engineers and vendor partners, driving delivery while establishing best practices … looking for: AI & GenAI Platform Leadership – Excellent experience designing and delivering AI solutions using Azure AI Foundry, Azure OpenAI, OpenAI, Azure AI Search, Claude and open-source LLMs, driving adoption across enterprise platforms. Engineering Leadership & Delivery – Deep software engineering expertise, strong Python skills, and hands-on delivery ...

Elastic, the Search AI Company, enables everyone to find the answers they need in real time, using all their data, at scale — unleashing the potential of businesses and people. The Elastic Search AI Platform, used by more than 50% of the Fortune 500, brings together the precision … search and the intelligence of AI to enable everyone to accelerate the results that matter. By taking advantage of all structured and unstructured data — securing and protecting private information more effectively — Elastic’s complete, cloud-based solutions for search, security, and observability help organizations deliver on the promise ...

evaluation loops Build multi-agent systems covering planning, delegation, tool use, safety constraints and monitoring Build retrieval pipelines: embeddings, vector stores, RAG and semantic search Apply knowledge modelling (ontologies, knowledge graphs) to improve reasoning and data alignment Integrate AI systems with enterprise platforms through APIs, tools and connectors … production-grade workflows Experience with at least one cloud AI ecosystem: Azure OpenAI, Google Vertex AI, AWS Bedrock or Anthropic Working knowledge of semantic modelling, ontologies or knowledge graphs Ability to turn open-ended business problems into working prototypes quickly Comfortable in client-facing delivery, ideally within a consultancy ...

interfaces, enabling secure and efficient interaction with enterprise systems, databases and external services. Develop compound AI architectures combining large language models with specialised models, semantic search, classification, re-ranking and deterministic workflows to improve accuracy, performance and cost efficiency. Build robust evaluation frameworks, automated testing, guardrails and observability ...

structured outputs and human‐in‐the‐loop patterns Practical experience designing and implementing RAG architectures Experience with document ingestion, chunking, embeddings and vector/semantic search Experience with prompt engineering and structured LLM outputs Experience with AI/LLM evaluation, testing and quality assurance Understanding of guardrails, grounding … GenAI/Agentic AI applications Azure AI & Cloud Services: Hands‐on experience building and deploying AI solutions on Azure, including Azure OpenAI, Azure AI Search, Azure AI Foundry, Cosmos DB, Redis, Azure Monitor/Application Insights, Managed Identity and Key Vault. #J-18808-Ljbffr ...

structured outputs and human-in-the-loop patterns Practical experience designing and implementing RAG architectures Experience with document ingestion, chunking, embeddings and vector/semantic search Experience with prompt engineering and structured LLM outputs Experience with AI/LLM evaluation, testing and quality assurance Understanding of guardrails, grounding … GenAI/Agentic AI applications Azure AI & Cloud Services: Hands-on experience building and deploying AI solutions on Azure, including Azure OpenAI, Azure AI Search, Azure AI Foundry, Cosmos DB, Redis, Azure Monitor/Application Insights, Managed Identity and Key Vault. If you receive suspicious outreach claiming ...

modelling and automated assessment systems. Develop and maintain data pipelines, services and infrastructure. Contribute to new AI capabilities, including Large Language Models (LLMs), embeddings, semantic search and Retrieval-Augmented Generation (RAG). Deploy, monitor and troubleshoot production data and machine learning systems. Work collaboratively with software engineers, data ...

including role definition, tool integration, planning, memory, and workflow orchestration using LangChain, CrewAI, AutoGen, ADK and LangGraph. Implement Retrieval-Augmented Generation (RAG) pipelines and semantic search using vector databases such as Pinecone and Chroma, including indexing, retrieval policies, and evaluation. Build and integrate agent tools (MCP) and APIs ...

multi-agent systems, including role definition, tool integration, planning, memory, and workflow orchestration using modern agent frameworks. Implement Retrieval-Augmented Generation (RAG) pipelines and semantic search with vector databases, including indexing, retrieval policies, and evaluation. Build and integrate agent tools and APIs to connect agents with external services ...

OpenAI APIs and/or Anthropic Claude. Practical experience with prompt engineering, system prompts, and evaluation techniques. Experience implementing RAG architectures, vector databases, and semantic search. Cloud & Platforms Strong experience with Google Cloud Platform (GCP), ideally Vertex AI. Experience deploying services using Docker/containerised workloads. Understanding of cloud ...

communication skills. AI & Modern Techniques Practical experience with large language models in applied or production settings. Experience with retrieval‐based approaches, including embeddings, semantic search, and ranking. Experience guiding or contributing to LLM‐powered systems involving multi‐step reasoning, tool use, or workflow orchestration. Strong judgment about when … MLOps practices, including experiment tracking, deployment, monitoring, and reproducibility. Experience collaborating with engineering teams on scalable system design. Familiarity with vector databases or search infrastructure such as Elasticsearch, OpenSearch, Qdrant, or similar. Nice to Have: Experience with search, information retrieval, recommendation, or knowledge systems at scale. Experience with ...

OpenAI or similar platforms, with exposure to techniques and frameworks such as retrieval‐augmented generation (RAG), Model Context Protocol (MCP) vector databases and embeddings, semantic search and agentic workflows. Full‐stack engineering, building web applications, dashboards, APIs and internal tools using established languages (JavaScript/Java/Python … productivity and business outcomes. Developing solutions on Microsoft Azure including App Services, Functions, Storage and managed database services, Azure AI Foundry and Azure AI Search Building and operating production services with appropriate monitoring, alerting, logging and observability tooling (e.g. New Relic), using platforms such as. Event‐driven architectures, messaging ...

reasoning systems that enable Protégé to decompose complex patent questions, plan multi-step analyses, and compose insights from multiple data sources.* Design retrieval and search architectures that deliver accurate, low-latency patent intelligence across both structured analytics and unstructured text corpora.* Define patterns for AI-driven enrichment and classification … Python for AI service development; working knowledge of C# or equivalent compiled language for enterprise microservice integration.* Hands-on experience with vector databases and semantic search pipeline design.* Experience with Model Context Protocol (MCP).* Experience with large-scale data platforms such as Databricks and search engines ...

reasoning systems that enable Protégé to decompose complex patent questions, plan multi-step analyses, and compose insights from multiple data sources.* Design retrieval and search architectures that deliver accurate, low-latency patent intelligence across both structured analytics and unstructured text corpora.* Define patterns for AI-driven enrichment and classification … Python for AI service development; working knowledge of C# or equivalent compiled language for enterprise microservice integration.* Hands-on experience with vector databases and semantic search pipeline design.* Experience with Model Context Protocol (MCP).* Experience with large-scale data platforms such as Databricks and search engines ...

reasoning systems that enable Protégé to decompose complex patent questions, plan multi-step analyses, and compose insights from multiple data sources. Design retrieval and search architectures that deliver accurate, low-latency patent intelligence across both structured analytics and unstructured text corpora. Define patterns for AI-driven enrichment and classification … Python for AI service development; working knowledge of C# or equivalent compiled language for enterprise microservice integration. Hands-on experience with vector databases and semantic search pipeline design. Experience with Model Context Protocol (MCP). Experience with large-scale data platforms such as Databricks and search engines ...

reasoning systems that enable Protégé to decompose complex patent questions, plan multi-step analyses, and compose insights from multiple data sources. Design retrieval and search architectures that deliver accurate, low-latency patent intelligence across both structured analytics and unstructured text corpora. Define patterns for AI-driven enrichment and classification … Python for AI service development; working knowledge of C# or equivalent compiled language for enterprise microservice integration. Hands-on experience with vector databases and semantic search pipeline design. Experience with Model Context Protocol (MCP). Experience with large-scale data platforms such as Databricks and search engines ...

software development and engineering expertise. Key areas of proficiency include: Programming Languages: Python, Java and Go. AI/ML: prompt engineering, LLMs, RAG, Semantic Search, Vector Databases, etc Behaviour-Driven Development (BDD) Testing: Cucumber, JBehave, Pytest-BDD, etc. CI/CD pipelines: Harness, Tekton, Jenkins, etc. Knowledge … veteran, or any other characteristic protected by law. If you are a person with a disability and need a reasonable accommodation to use our search tools and/or apply for a career opportunity review Accessibility at Citi. View Citi’s EEO Policy Statement and the Know Your Rights ...