26 to 50 of 79 Retrieval-Augmented Generation Jobs in London

code already in place Requirements - 5+ years as an AI/ML engineer delivering NLP and ML models into production SaaS - Production LLM experience: RAG, fine-tuning, evaluation, monitoring - Strong Python, including building APIs and integrating models into applications - NLP frameworks such as Hugging Face Transformers, PyTorch, spaCy or TensorFlow ...

hands-on experience taking AI systems into production. Key experience includes: Production Python PyTorch, Hugging Face Transformers or similar Strong hands-on LLM experience RAG, vector search, prompting, tool use and agent orchestration Designing and running model evaluations Cloud deployment, containers and CI/CD Understanding AI attack surfaces ...

across a range of AI and cloud projects. Responsibilities will include: Designing and delivering Generative AI and Machine Learning solutions Building applications using LLMs, RAG frameworks and AI orchestration tools Working directly with clients to understand business challenges and define AI-driven solutions Leading architecture and engineering decisions across Azure … experience building AI-powered applications and deploying them into production Software Engineering or Product Engineering background Strong Python development skills Experience working with LLMs, RAG architectures and modern AI frameworks Multi-cloud experience across Azure, AWS and GCP Strong understanding of cloud-native architectures and scalable application design Experience with ...

enjoy building real solutions. You'll use Python as your primary development language, developing APIs, services and AI applications using technologies such as LLMs, RAG, AI agents and vector search. You'll work across the development lifecycle, helping take GenAI ideas and POC's through to robust, production-ready applications … enterprise clients. What you'll be doing: Build production applications and APIs using Python and FastAPI Develop LLM, RAG and AI agent solutions Build RAG pipelines covering embeddings, retrieval and generation Work with OpenAI, Anthropic, Mistral, Llama and similar LLMs Use LangChain, LangGraph, CrewAI or similar ...

enjoy building real solutions. You'll use Python as your primary development language, developing APIs, services and AI applications using technologies such as LLMs, RAG, AI agents and vector search. You'll work across the development lifecycle, helping take GenAI ideas and POC's through to robust, production-ready applications … enterprise clients. What you'll be doing: Build production applications and APIs using Python and FastAPI Develop LLM, RAG and AI agent solutions Build RAG pipelines covering embeddings, retrieval and generation Work with OpenAI, Anthropic, Mistral, Llama and similar LLMs Use LangChain, LangGraph, CrewAI or similar ...

fundamentally change how analysts work and how Fitch operates Drive breakthrough AI innovation and experimentation boldly – Lead exploration of generative AI, multi-agent systems, RAG architectures, model fine-tuning, prompt engineering, and other emerging ML technologies; create cutting-edge proofs-of-concept; evaluate what's transformative versus what's hype … environments Advanced generative AI expertise – Extensive hands-on experience developing and integrating generative AI solutions, working with large language models, building agentic systems, implementing RAG architectures, and training/fine-tuning neural networks using frameworks like PyTorch Bachelor's degree in Machine Learning, Computer Science, Data Science, Applied Mathematics ...

robust error handling. Build MCP clients and servers that connect agents securely to repositories, enterprise data sources, development tools and business systems. Implement RAG and context-engineering solutions using structured and unstructured data, embeddings, vector search and knowledge stores. Use Claude Code and AI-assisted engineering practices across requirements, coding … control and CI/CD workflows. MCP client/server development or comparable secure tool-integration patterns for agentic applications. Agent orchestration, tool calling, RAG, context engineering, vector databases, event-driven integration and human approval workflows. Deployment through Anthropic APIs and/or Amazon Bedrock or Google Cloud Vertex ...

controls Experience with experiment tracking and MLOps tooling (MLflow, Weights & Biases, Data Version Control) Experience developing LLM/GenAI applications, including prompt engineering and RAG architectures Familiarity with LLMOps tooling such as LangSmith, LangChain, or LangGraph Understanding of model evaluation, validation techniques, and production monitoring Experience working in cross-functional … well help you with them: Experience with advanced LLM techniques: agents, tool use, and agentic workflows Experience with vector databases (Pinecone, Weaviate, pgvector) for RAG applications Experience with feature stores (Feast, AWS Feature Store) Experience with containerisation (Docker) and orchestration (Kubernetes, ECS) Familiarity with Infrastructure as Code (Terraform, CloudFormation) Experience ...

controls Experience with experiment tracking and MLOps tooling (MLflow, Weights & Biases, Data Version Control) Experience developing LLM/GenAI applications, including prompt engineering and RAG architectures Familiarity with LLMOps tooling such as LangSmith, LangChain, or LangGraph Understanding of model evaluation, validation techniques, and production monitoring Experience working in cross-functional … help you with them: Experience with advanced LLM techniques: agents, tool use, and agentic workflows Experience with vector databases (Pinecone, Weaviate, pgvector) for RAG applications Experience with feature stores (Feast, AWS Feature Store) Experience with containerisation (Docker) and orchestration (Kubernetes, ECS) Familiarity with Infrastructure as Code (Terraform, CloudFormation) Experience with ...

controls Experience with experiment tracking and MLOps tooling (MLflow, Weights & Biases, Data Version Control) Experience developing LLM/GenAI applications, including prompt engineering and RAG architectures Familiarity with LLMOps tooling such as LangSmith, LangChain, or LangGraph Understanding of model evaluation, validation techniques, and production monitoring Experience working in cross-functional … help you with them: Experience with advanced LLM techniques: agents, tool use, and agentic workflows Experience with vector databases (Pinecone, Weaviate, pgvector) for RAG applications Experience with feature stores (Feast, AWS Feature Store) Experience with containerisation (Docker) and orchestration (Kubernetes, ECS) Familiarity with Infrastructure as Code (Terraform, CloudFormation) Experience with ...

analysts and financial markets operate Work at the cutting edge of ML technology – Experiment with the latest LLMs and foundation models, implement novel RAG architectures, build agentic systems, fine-tune neural networks, and leverage enterprise-scale GPU clusters and cloud infrastructure; substantial conference and training budgets to stay … financial technology We'll Count on You To: Design and build transformative ML systems – Lead the development of advanced generative AI solutions, agentic workflows, RAG architectures, and intelligent platforms using PyTorch, modern ML frameworks, and large language models; write production-quality code that scales and performs Drive AI innovation through ...

engineering * Experience of agile product management * Confidence with APIs and related integration and machine-delivery services * Working fluency with modern AI product concepts: RAG, agents, evaluation, and prompt/structured-output patterns * Bachelor's degree in engineering, computer science, finance or a related field, or equivalent experience NICE TO HAVE ...

good working knowledge of generative and agentic AI and technologies such as Microsoft 365 Copilot, Copilot Studio, Azure AI Foundry, AI agents and RAG-based solutions . An understanding of responsible AI, information security, data protection, governance and compliance considerations. Experience prioritising competing demands based on business value, risk, feasibility ...

growing London-based team and play a key role in designing and developing cutting-edge agentic AI systems that will power the next generation of enterprise automation. What You'll Be Doing Designing and developing agentic AI systems capable of autonomous decision-making and task execution. Building sophisticated … Azure AI Services, and Azure Machine Learning. Knowledge of modern AI frameworks including LangChain, Hugging Face, PyTorch, or similar technologies. Deep understanding of LLMs, RAG architectures, vector databases, prompt engineering, agentic AI, and multi-agent systems. Experience deploying, monitoring, and optimising AI solutions in production environments. A builder's mindset ...

Inside IR35 Start: Mid October Contract - 6 Months Python AI Engineer required to develop production-grade Python services for Generative AI and complex RAG solutions. You will work across AI workflow orchestration, information retrieval, evidence processing, LLM integration, response generation and validation This role requires strong … production Python experience and practical experience delivering Generative AI and RAG solutions beyond proof of concept. Job Responsibilities/Objectives: Design, develop and maintain production-grade Python services for Generative AI and RAG solutions. Build and integrate LLM workflows using structured outputs, tool calling, schema validation and controlled fallbacks. Implement ...

benchmarking, bias and fairness assessment, alignment and misalignment analysis, adversarial testing, and red-teaming Strong LLM/GenAI engineering fluency: prompting strategies, retrieval-augmented generation, context and memory design, function/tool calling, guardrails, observability, and failure-mode analysis (e.g., prompt injection, tool misuse ...

major public sector programme. This is an opportunity to work at the cutting edge of AI engineering, developing intelligent applications that combine LLMs, RAG and autonomous agent workflows with robust Python engineering and Microsoft Azure technologies. You'll be working within a product squad, turning complex requirements into secure, scalable … state management, routing and human-in-the-loop controls. GenAI & LLMs: Develop LLM-powered applications using Python, prompt engineering, structured outputs and context management. RAG & Knowledge Retrieval: Build end-to-end RAG pipelines covering document ingestion, chunking, embeddings, vector search, reranking and evidence grounding. AI Quality & Assurance: Implement ...

major public sector programme. This is an opportunity to work at the cutting edge of AI engineering, developing intelligent applications that combine LLMs, RAG and autonomous agent workflows with robust Python engineering and Microsoft Azure technologies. You'll be working within a product squad, turning complex requirements into secure, scalable … state management, routing and human-in-the-loop controls. GenAI & LLMs: Develop LLM-powered applications using Python, prompt engineering, structured outputs and context management. RAG & Knowledge Retrieval: Build end-to-end RAG pipelines covering document ingestion, chunking, embeddings, vector search, reranking and evidence grounding. AI Quality & Assurance: Implement ...

deliver GenAI and Agentic AI products. The individual must have hands-on experience developing production-grade GenAI/Agentic AI solutions using LLMs, RAG and agentic workflow technologies. The role requires strong Python software engineering skills alongside practical experience designing reliable, secure and maintainable AI-enabled applications. Skills required Strong … LangGraph Strong understanding of LLM workflow design, including state, routing, tools, 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/ ...

architecture and prototyping through to deployment, monitoring and continuous evaluation. Key responsibilities: Design and deliver production GenAI and multi-agent systems Build agentic workflows, RAG solutions, tool use and multi-step orchestration Define evaluation strategies and implement AI observability Design secure AWS deployment architectures Build CI/CD pipelines … skills Hands-on experience with LangGraph, LangChain, LlamaIndex, CrewAI or similar Experience with AWS, particularly Bedrock, Lambda, ECS, EKS or SageMaker Strong understanding of RAG, agentic AI and multi-agent architectures Experience with CI/CD, cloud infrastructure and application deployment Comfortable working directly with clients and senior stakeholders Experience ...

document intelligence pipelines that extract, structure and reason over long, messy financial documents such as filings, decks, models and data rooms. Develop retrieval-augmented generation systems, including chunking, embeddings, vector search, re-ranking and citation, so that every answer can be traced … learning or software engineering, with production ML experience and strong Python. Hands-on experience shipping LLM-based or NLP systems to real users, including RAG, agents and tool use, and the ability to explain the design and trade-off decisions behind them. A rigorous approach to evaluation: you can define ...

Python in an enterprise, high-bar engineering environment. Demonstrated experience designing, building, and deploying large language model applications, including prompt engineering, evaluation, retrieval-augmented generation, and agent orchestration. Familiarity with modern generative AI components such as large language model APIs, vector stores, embeddings, tool ...

Python in an enterprise, high-bar engineering environment. Demonstrated experience designing, building, and deploying large language model applications, including prompt engineering, evaluation, retrieval-augmented generation, and agent orchestration. Familiarity with modern generative AI components such as large language model APIs, vector stores, embeddings, tool ...

Python in an enterprise, high-bar engineering environment. Demonstrated experience designing, building, and deploying large language model applications, including prompt engineering, evaluation, retrieval-augmented generation, and agent orchestration. Familiarity with modern generative AI components such as large language model APIs, vector stores, embeddings, tool ...

autonomous action execution. Architect multi agent systems, orchestration patterns, and scalable AI microservices. Build AI applications using Python and Azure OpenAI technologies. Develop RAG architectures and integrate vector search solutions. Implement orchestration workflows using Semantic Kernel and LangGraph. Integrate enterprise systems, APIs, and tools using MCP and similar frameworks. Establish … Generative AI solutions. Strong expertise in Azure OpenAI, Azure AI Foundry, Azure AI Search, Semantic Kernel, and LangGraph. Experience building multi agent architectures, RAG solutions, and complex orchestration workflows. Strong Python development skills with experience building scalable microservices. Knowledge of MCP (Model Context Protocol) and AI tool integration frameworks. Experience ...