1 to 25 of 98 Permanent Retrieval-Augmented Generation Jobs in the City of London

will leverage managed AI services across GCP and Azure to deliver features like semantic search, retrieval-augmented generation (RAG), and intelligent data enrichment. Working closely with Data and ML Engineers, you will define patterns, select technologies, and ensure our solutions are secure, performant … Search with embeddings. Cost & Performance : Establish strategies for latency optimization and cost control across clouds. AI Enablement & Delivery RAG System Design : Implement retrieval-augmented generation patterns for small, volatile data chunks; ensure grounding and factuality. Evaluation & Observability : Define quality metrics (precision/recall, groundedness ...

implement robust, goal-driven AI agents using leading frameworks like LangChain, LangGraph, and the Google Agent Development Kit (ADK). Develop and Evaluate RAG Pipelines: Engineer and optimize end-to-end Retrieval-Augmented Generation (RAG) systems, including data ingestion, chunking strategies, and implementing rigorous … Prompt Engineering and hands-on experience with model fine-tuning techniques including PEFT and QLoRA. Proven experience with models like Gemini, and Llama 3. RAG & Vector Databases: Deep expertise in RAG architecture and evaluation metrics. Proven experience with Vector Databases such as Milvus, Pinecone, or Chroma. Software & Cloud Engineering: Programming ...

field. Demonstrable experience of deploying modern AI/ML solutions into production, including prompt engineering, retrieval-augmented generation (RAG), model evaluation, and monitoring using metrics (e.g. precision, recall, NDCG and drift detection). Strong Python skills with a grounding in software engineering best practices ...

design, build, and deliver next-generation AI systems. You will work across LLMs, retrieval-augmented generation (RAG), and modern agent frameworks to transform large, unstructured data into meaningful insights and production-ready capabilities. This is a hands-on role within a growing … entity extraction, and intelligent automation. Design scalable data and streaming pipelines capable of handling large, heterogeneous datasets. Build and optimize vector search, embeddings, and RAG systems to support high-quality retrieval. Deliver production-ready APIs, services, and model inference systems. Manage deployment, monitoring, observability, and continual improvement of ML models. ...

Chatbots - Document Q&A systems - Report generators - Code assistants - Summarization tools Apply prompt engineering, Retrieval-Augmented Generation (RAG), and context-aware pipelines to enhance model accuracy and relevance. Integrate AI models with enterprise systems, APIs, and data stores using Python, Java, or Node.js. Collaborate … LLMs (e.g., GPT, LLaMA, Claude, Mistral), Transformers, and Diffusion models. Experience with Hugging Face Transformers, LangChain, LLM orchestration frameworks, and prompt tuning. Familiarity with RAG pipelines, embedding models, and vector databases. Experience with cloud platforms (AWS, GCP, Azure) and AI/ML services. Knowledge of MLOps tools and practices (e.g. ...

help drive innovation across cutting-edge AI initiatives — from chatbots and voice assistants to advanced retrieval-augmented generation (RAG) systems and agentic workflows. The Role You’ll work closely with the AI Engineering and Data Science teams to: Develop and prototype AI-driven solutions … across customer-facing and internal applications. Build and optimise LLM-based assistants , RAG pipelines , and agentic AI workflows . Collaborate on the architecture and deployment of scalable AI solutions (with support from engineering). Partner with stakeholders to translate business needs into practical, intelligent systems. Mentor junior team members ...

help drive innovation across cutting-edge AI initiatives — from chatbots and voice assistants to advanced retrieval-augmented generation (RAG) systems and agentic workflows. The Role You’ll work closely with the AI Engineering and Data Science teams to: Develop and prototype AI-driven solutions … across customer-facing and internal applications. Build and optimise LLM-based assistants , RAG pipelines , and agentic AI workflows . Collaborate on the architecture and deployment of scalable AI solutions (with support from engineering). Partner with stakeholders to translate business needs into practical, intelligent systems. Mentor junior team members ...

Responsibilities: Design, build, and deploy Large Language Model (LLM)-driven applications into production Develop retrieval-augmented generation (RAG) systems for real-time insights from performance and wearable data Optimise and fine-tune LLMs for efficiency, scalability, and accuracy in production environments Build and maintain … software engineering fundamentals Proven experience working with LLMs in production (fine-tuning, prompt engineering, or API integrations) Proficiency in Python Experience designing and deploying RAG pipelines (vector databases, embeddings, retrieval optimisation) Academic Excellence: BSc or MSc in Computer Science, AI, Data Science, or related technical field from ...

digital capabilities across all of these services. With our thought leadership and culture of innovation, we apply industry expertise, diverse skills and next-generation technology to each business challenge. We believe in inclusion and diversity and supporting the whole person. Our core values comprise of Stewardship, Best People … experience with SAP AI Core, Generative AI Hub, and SAP HANA Cloud Vector Engine (for Retrieval-Augmented Generation, RAG). Proven ability to embed AI and advanced analytics into SAP business processes, leveraging SAP’s Business AI suite and integrating external LLMs (e.g., OpenAI ...

with the team to develop GenAI proof-of-concepts (POCs) for clients using technologies like Retrieval-Augmented Generation (RAG) and intelligent agents. Scale existing POCs to production-ready solutions for customer use. Design and develop Full Stack applications for both GenAI and non-GenAI ...

context and tool interfaces for agents. LLM integration patterns, including prompt orchestration and tool calling. Retrieval-Augmented Generation (RAG) for dynamic context injection. Understanding of user-centric design for AI interfaces and intelligent automation. Experience with AI frameworks (PyTorch, Tensorflow, Hugging Face etc.). ...

with the team to develop GenAI proof-of-concepts (POCs) for clients using technologies like Retrieval-Augmented Generation (RAG) and intelligent agents. Scale existing POCs to production-ready solutions for customer use. Design and develop Full Stack applications for both GenAI and non-GenAI ...

with the team to develop GenAI proof-of-concepts (POCs) for clients using technologies like Retrieval-Augmented Generation (RAG) and intelligent agents. Scale existing POCs to production-ready solutions for customer use. Design and develop Full Stack applications for both GenAI and non-GenAI ...

with the team to develop GenAI proof-of-concepts (POCs) for clients using technologies like Retrieval-Augmented Generation (RAG) and intelligent agents. Scale existing POCs to production-ready solutions for customer use. Design and develop Full Stack applications for both GenAI and non-GenAI ...

Software Engineer | Python | RAG | Retrieval Augmented Generation | DAG | Dagster | London, UK The role We are hiring an agent-focused software engineer to build internal agentic frameworks for our discovery product. You will define and implement the operating system that allows scientists to run repeatable … Ability to communicate clearly across disciplines and translate real scientific workflows into robust software. Nice-to-have experience Experience with agent frameworks, retrieval-augmented generation, or multi-agent systems. Familiarity with ML experiment tracking or model registries and data orchestration platforms. Exposure to knowledge ...

environments. This is an end-to-end role focusing on the design and implementation of applied AI capabilities, from building secure knowledge-based chat (RAG solutions) over internal documentation and codebases, to developing complex agentic workflows that integrate deeply within their product suite. Key Responsibilities Define and execute … core business objectives. Implement documentation ingestion pipelines for structured knowledge bases. Build secure, enterprise-grade Retrieval-Augmented Generation (RAG) systems. Collaborate with engineering teams to embed AI features into existing and new products. Design and deploy agentic workflows to automate multi-step tasks across ...

building and deploying applied AI systems, with a particular focus on large language models (LLMs), retrieval-augmented generation (RAG), and conversational AI. This is a hands-on role operating across the full AI lifecycle, from experimentation and prototyping through to production deployment. … customer impact. Key Responsibilities Leading the development of AI proof-of-concepts and production systems, including LLM-powered assistants and chatbots. Designing and implementing RAG pipelines using vector search, embeddings and knowledge retrieval strategies. Fine-tuning, evaluating and deploying language models, with a focus on response quality, reliability ...

engineering best practices, delivery processes, and a high-performance team culture. Technical Ownership Lead architecture and development of LLM-powered and agentic applications , including RAG systems, chat/workflow agents, and domain-specific AI services. Drive technical direction with sound judgement and pragmatic decision-making. Build and deploy production-grade … systems into production. Deep expertise in: LLMs & transformer-based models Agentic frameworks (e.g., LangChain, LangGraph) Retrieval-Augmented Generation (RAG) Python Building or integrating LLMs into products or workflows Working with GenAI frameworks and tooling Designing or optimising prompt pipelines Deploying or supporting GenAI features ...

foundation in software engineering principles for building scalable, maintainable, and production-ready AI systems. Experience in designing and implementing enterprise-grade AI solutions, including RAG-based solutions with LLMs and vector databases (e.g., Pinecone, Weaviate, FAISS). Bachelor's or Master's degree in Computer Science, Engineering, or a related ...

foundation in software engineering principles for building scalable, maintainable, and production-ready AI systems. Experience in designing and implementing enterprise-grade AI solutions, including RAG-based solutions with LLMs and vector databases (e.g., Pinecone, Weaviate, FAISS). Proven experience in full stack development and AI/ML system implementation within ...

create high-quality pre-trained datasets, fine-tuned industry-specific Large Language Models(LLMs), and Retrieval-Augmented Generation (RAG) pipelines supported by vector databases. Our innovations can reduce Generative Artificial Intelligence(Gen AI) costs by up to 80% and bring Gen AI solutions ...

teaching. Required experience: Previously built and deployed multi-agent systems end-to-end Strong hands-on expertise with LangGraph Experience with knowledge graphs, RAG and LLM tool orchestration Proven software engineering fundamentals (Python preferred) Solid MLOps grounding: Kubernetes, CI/CD, Docker, cloud platforms (GCP/AWS/Azure) Comfortable ...

Doing: Designing, developing, and deploying machine learning and AI models Designing, developing, and deploying LLM applications (e.g. GPT, LLaMA, Claude) integrated with RAG pipelines Implementing end-to-end workflows: from data acquisition, cleaning, and feature engineering to model training, deployment, and monitoring Building scalable pipelines and APIs for AI services ...

Python and familiarity with deep learning/NLP libraries (LangChain, PyTorch, TensorFlow, HuggingFace Transformers). Experience with building Q&A systems and retrieval-augmented generation pipelines. Knowledge of vector databases or semantic search concepts. Familiarity with cloud AI platforms (AWS Bedrock, Azure OpenAI … deploying AI workloads to Azure Container Apps (ACA), Azure Kubernetes Service (AKS), or serverless functions (Azure Functions) for event-driven agent triggers. Experience implementing RAG using Azure AI Search (vector, semantic, and hybrid search) and OneLake/Microsoft Fabric. Nice to Have Skills Certification: Microsoft Certified: Azure AI Engineer Associate ...

/Vertex AI , including fine-tuning, vector search, and low-latency inference. Build end-to-end LLM applications , leveraging RAG (Retrieval-Augmented Generation) , agentic workflows, and prompt engineering. Implement robust evaluation frameworks to monitor LLM quality, hallucinations, token usage, and content safety. Develop … Looking For Essential 5+ years' experience in machine learning engineering or applied AI roles. Recent, demonstrable experience with LLMs, Generative AI, and/or RAG-based systems . Strong Python skills using frameworks such as PyTorch, TensorFlow, Hugging Face, or Google GenAI . Experience with vector databases and retrieval ...