22 of 22 Semantic Search Jobs in London

looking for a founding AI engineer to help design and build the core of its AI platform. AI is central to the product, powering semantic search, intelligent matching, assistants, and personalised experiences across web and mobile. You’ll work closely with the founders to design and deliver creative … features that genuinely change how people discover and book services. What you’ll be doing Architect and build AI-driven backend services powering semantic search, natural language interfaces, recommendations and assistants Integrate and deploy LLM APIs (OpenAI, Anthropic, Cohere) and open-source AI frameworks (LangChain, LlamaIndex, LangGraph) into ...

looking for a founding AI engineer to help design and build the core of its AI platform. AI is central to the product, powering semantic search, intelligent matching, assistants, and personalised experiences across web and mobile. You’ll work closely with the founders to design and deliver creative … features that genuinely change how people discover and book services. What you’ll be doing Architect and build AI-driven backend services powering semantic search, natural language interfaces, recommendations and assistants Integrate and deploy LLM APIs (OpenAI, Anthropic, Cohere) and open-source AI frameworks (LangChain, LlamaIndex, LangGraph) into ...

Recommendation and ranking services Classification, quality scoring, and enrichment pipelines Implement and evolve the AI/ML platform, including: Feature and embeddings stores Vector search/semantic search infrastructure Evaluation dashboards, prompt/version management, and feedback loops Own services end-to-end: from design and implementation … teams. Hands-on experience with AI/ML or GenAI in production, such as: Fine-tuning or integrating transformer models Building RAG pipelines and semantic search Working with vector databases (e.g., Pinecone, Weaviate, Milvus, OpenSearch, etc.) Self-motivated and proactive, able to work independently where needed while contributing ...

Recommendation and ranking services Classification, quality scoring, and enrichment pipelines Implement and evolve the AI/ML platform, including: Feature and embeddings stores Vector search/semantic search infrastructure Evaluation dashboards, prompt/version management, and feedback loops Own services end-to-end: from design and implementation … teams. Hands-on experience with AI/ML or GenAI in production, such as: Fine-tuning or integrating transformer models Building RAG pipelines and semantic search Working with vector databases (e.g., Pinecone, Weaviate, Milvus, OpenSearch, etc.) Self-motivated and proactive, able to work independently where needed while contributing ...

Knowledge Systems Implementation of Retrieval-Augmented Generation (RAG) pipelines Experience with vector databases such as CockroachDB, Pinecone, or similar Embedding model optimisation and semantic search Context window management and chunking strategies MCP & Tool Integration Model Context Protocol (MCP) implementation LLM tool calling and API design AWS Lambda integration ...

Knowledge Systems Implementation of Retrieval-Augmented Generation (RAG) pipelines Experience with vector databases such as CockroachDB, Pinecone, or similar Embedding model optimisation and semantic search Context window management and chunking strategies MCP & Tool Integration Model Context Protocol (MCP) implementation LLM tool calling and API design AWS Lambda integration ...

Research, MLOps, Data Pipelines, Prompt Engineering, Model Fine-Tuning, Cloud Computing, AWS, Azure, Google Cloud, AI Infrastructure, Transformers, Reinforcement Learning, Vector Databases, Pinecone, Weaviate, Semantic Search, API Development, AI Deployment, Model Serving, AI Automation, Early Stage Startup, AI Startups, Tech Startup, Machine Intelligence, Applied AI, AI Applications ...

team. The ideal candidate will bring deep expertise in building and deploying AI/ML solutions, particularly in areas like NLP, document understanding, and search/retrieval systems. You will work in a dynamic environment, collaborating across teams to design scalable AI-driven solutions and bring them into production. … optimization. Work with LLM architectures and frameworks (OpenAI, Anthropic, LangChain, LlamaIndex) to build scalable and intelligent applications. Utilize vector databases (e.g., FAISS, Azure AI Search) and embedding models for semantic search and retrieval tasks. Execute and iterate on PoCs rapidly to evaluate feasibility and solution effectiveness. Collaborate ...

areas: Computer Vision: Developing and optimizing models for image recognition, object detection, and video analytics. NLP: Building sophisticated systems for sentiment analysis, entity extraction, semantic search, and RAG architectures leveraging LLMs. Generative AI: Exploring and implementing cutting-edge GenAI techniques for content creation, data augmentation, and innovative product ...

ship backend systems from day one — scalable architectures, APIs, and AI-powered tools. Build and deploy LLM-based applications using frameworks such as LangChain, semantic search, RAG, and fine-tuning (SFT/RL). Develop backend logic and data pipelines to power intelligent automation and real-time processing. ...

ship backend systems from day one — scalable architectures, APIs, and AI-powered tools. Build and deploy LLM-based applications using frameworks such as LangChain, semantic search, RAG, and fine-tuning (SFT/RL). Develop backend logic and data pipelines to power intelligent automation and real-time processing. ...

testing and evaluation framework for all AI solutions, including LLM-based tools, RAG systems, and third-party platforms. Define and document quality standards for semantic accuracy, factual consistency, bias, tone, and relevance. Develop reusable testing templates, data sets, and evaluation methods that can be scaled and maintained by internal … Strong hands-on experience in testing and evaluation of AI or software systems, ideally with NLP or LLM-based applications. Understanding of prompt evaluation, semantic search, and LLM behaviour (accuracy, hallucination, bias, tone, etc.). Familiarity with tools like Trulens, HumanLoop, PromptLayer, or similar; experience designing QA approaches ...

DTAC) Frontend React TypeScript Tailwind Component-driven development AI/RAG/Knowledge Pipelines LLM-powered features RAG pipelines (embedding models, chunking strategies, semantic search) Document extraction/processing (PDF parsing, OCR, agentic pipelines) Clinical content ingestion workflows Evaluation frameworks for safe medical AI responses … support. Nice to Have Experience coding in TypeScript, JavaScript, Python, or similar. Understanding of cloud systems (AWS preferred). Familiarity with LLMs, embeddings, or semantic search. A portfolio of side projects, tools, or apps you’ve built (clinical or not). Experience in a startup or fast-moving environment. ...

DTAC) Frontend React TypeScript Tailwind Component-driven development AI/RAG/Knowledge Pipelines LLM-powered features RAG pipelines (embedding models, chunking strategies, semantic search) Document extraction/processing (PDF parsing, OCR, agentic pipelines) Clinical content ingestion workflows Evaluation frameworks for safe medical AI responses … support. Nice to Have Experience coding in TypeScript, JavaScript, Python, or similar. Understanding of cloud systems (AWS preferred). Familiarity with LLMs, embeddings, or semantic search. A portfolio of side projects, tools, or apps you’ve built (clinical or not). Experience in a startup or fast-moving environment. ...

experience in production environments. Strong AWS proficiency - hands-on experience building and deploying systems in the cloud. Familiarity with embedding models, chunking strategies, and semantic search. Experience working in a small team or startup environment. A pragmatic problem-solver who balances speed with sustainability. Passion for writing maintainable, scalable ...

experience in production environments. Strong AWS proficiency - hands-on experience building and deploying systems in the cloud. Familiarity with embedding models, chunking strategies, and semantic search. Experience working in a small team or startup environment. A pragmatic problem-solver who balances speed with sustainability. Passion for writing maintainable, scalable ...

opportunity to sit at the heart of product design - translating human problem-solving processes into rigorous mathematical, algorithmic and optimisation models that power summarisation, semantic search, and decision-support workflows.You'll lead the design and validation of core algorithms, working closely with Data Scientists and Engineers to embed … algebraic modelling, graph theory, optimisation and statistics to complex, unstructured data problemsPrototyping and validating algorithms in Python and MATLABShaping the mathematical backbone of vector search, intent extraction and LLM-driven workflowsProducing clear, auditable documentation in LaTeX and JupyterActing as the mathematical authority across the platform and mentoring others where ...

Databases & Embeddings Strong understanding of vector database concepts, indexing strategies, and performance trade-offs Design and implementation of embedding generation pipelines Optimization techniques for semantic search and retrieval accuracy Effective chunking strategies for document ingestion and processing Experience with CockroachDB deployment and management is beneficial Document Processing Experience ...

Databases & Embeddings Strong understanding of vector database concepts, indexing strategies, and performance trade-offs Design and implementation of embedding generation pipelines Optimization techniques for semantic search and retrieval accuracy Effective chunking strategies for document ingestion and processing Experience with CockroachDB deployment and management is beneficial Document Processing Experience ...

with AWS services including Glue, Step Functions, S3, DynamoDB, Redshift, Lambda, and EventBridge. Build and optimise vector database solutions and embedding generation pipelines for semantic search. Implement document processing workflows (PDF parsing, OCR, metadata extraction). Integrate data from REST APIs , PIM systems, and potentially SAP. Ensure data quality … boto3) and SQL (complex queries, optimisation). Experience with AWS Glue , Step Functions , and event-driven architectures . Knowledge of vector databases , embeddings, and semantic search strategies. Familiarity with document parsing libraries (PyPDF2, pdfplumber, Textract) and OCR tools. Understanding of data governance , schema validation, and master data management. ...

with AWS services including Glue, Step Functions, S3, DynamoDB, Redshift, Lambda, and EventBridge. Build and optimise vector database solutions and embedding generation pipelines for semantic search. Implement document processing workflows (PDF parsing, OCR, metadata extraction). Integrate data from REST APIs , PIM systems, and potentially SAP. Ensure data quality … boto3) and SQL (complex queries, optimisation). Experience with AWS Glue , Step Functions , and event-driven architectures . Knowledge of vector databases , embeddings, and semantic search strategies. Familiarity with document parsing libraries (PyPDF2, pdfplumber, Textract) and OCR tools. Understanding of data governance , schema validation, and master data management. ...

across countries in a collaborative, inclusive environment. If you enjoy translating deep technical insight into content that performs across both traditional and AI-driven search, this is the role for you. We offer An interesting position in a leading company, where you will play a central role … user behaviour data to measure performance, identify content gaps and continuously optimise based on traffic, engagement and conversion. • Optimise content for both traditional search (SEO) and AI-driven discovery (structure, metadata, intent, semantic search, RAG-friendly formats). • Build and maintain editorial calendars aligned with commercial priorities ...