12 of 12 Retrieval-Augmented Generation Jobs in the City of Westminster

unsupervised learning, reinforcement learningand LLMs. Experience with the latest AI engineering approaches such asprompt engineering, retrieval-augmented generation (RAG)and agentic AI. Strong Python skills with a grounding in software engineering best practices (CI/CD, testing, code reviews etc). Expertisein data engineering ...

learning operations practices Strong working knowledge of large language models (LLMs), including prompting, fine-tuning, retrieval-augmented generation (RAG), and evaluation techniques, and the ability to apply them to real product challenges Experience with agentic AI frameworks and libraries in Python, such ...

high-quality production code while guiding technical direction Deep hands-on expertise building enterprise AI applications using large language models, AI agents, retrieval-augmented generation, prompt engineering, orchestration frameworks, evaluation methods, and model optimisation techniques Proven ability to take complex AI solutions from prototype … pipelines, and platform capabilities that support real-time and batch AI workloads at enterprise scale Implement advanced large language model applications using retrieval-augmented generation, prompt orchestration, evaluation frameworks, model optimisation, agentic workflows, and tool integration Make key technical decisions while remaining accountable ...

architectures, including Kafka Agentic AI and ML Commercial and open‐source LLMs integrated into agentic workflows Tooling for agent orchestration, retrieval‐augmented generation, vector storage, and evaluation Schema validation and structured data handling AI-assisted development Use of AI-assisted and agentic development tools ...

know what it means to balance craft, ownership, and speed Familiarity with tools that power today's AI agents: eval frameworks, agent tooling, RAG pipelines, and prompt engineering Prior experience with React, TypeScript, and/or Go Previous roles where you interfaced with customers or led technical projects with external ...

code You have experience working with large-scale, unstructured text data and LLMs — including prompt design, evaluation (e.g., golden sets, LLM‐as‐judge), and RAG patterns You have demonstrated ability to mentor junior data scientists, balance speed, risk, and analytical rigor You have experience with advanced visualization techniques/best ...

launch and architecting AI systems on cloud platforms (e.g., GCP). Experience building pipelines for structured and unstructured data using both vector databases and RAG-like architectures to power enterprise AI solutions. Experience leading technical discovery sessions with customers. Active, or the ability to obtain, a Security Check ...

outcomes. Even better... Experience building or deploying AI/LLM agents in production hands-on with the tools behind them (eval frameworks, agent tooling, RAG, prompt engineering) working closely with technical counterparts. You've been a founder, founding team member, or operator you know how to balance craft, ownership ...

event-driven architectures, including Kafka Agentic AI and ML Commercial and open-source LLMs integrated into agentic workflows Tooling for agent orchestration, retrieval-augmented generation, vector storage, and evaluation Strong schema, validation, and state management practices AI-assisted developmen t Fluency with AI-assisted ...

Kubernetes, and cloud-native infrastructure. Design and deploy scalable batch and real-time ML pipelines supporting customer-facing applications. Develop and operationalise LLM applications, RAG systems, and Generative AI capabilities for content understanding, summarisation, classification, and recommendation use cases. Build evaluation frameworks and observability solutions to monitor model quality, reliability … Intelligence, Statistics, Data Science, or a related STEM field. Experience applying Generative AI and LLMs to customer-facing products and designing, building, or scaling RAG systems. Experience in search, ranking, recommendations, personalisation, content intelligence, moderation, NLP, computer vision, or related AI domains. Experience with Airflow or comparable workflow orchestration platforms. ...

plane for staff and customer authentication. Contribute to AI-enabled quotation and knowledge tools, including human-in-the-loop quote drafting and retrieval-augmented knowledge features. Collaborate closely with mobile, product and engineering colleagues where your APIs are consumed across different surfaces. Take part in architecture … through to delivery. Useful Additional Experience Exposure to React or React Native, particularly where APIs support web or mobile products. Experience with retrieval-augmented generation, vector search or integrating LLM-based features into production products. Experience working in a scale-up, transformation programme ...

need of a Python engineer to support a customer with building an AI Chatbot using Python and LlamaIndex. Key Technologies: Python 3.12+ LlamaIndex/RAG Azure AI Foundry/OpenAI Typesense/Vector Search PostgreSQL/Pydantic Plotly Dash Key Duties: Develop and enhance production-grade Python AI applications … chatbot capabilities. Build and improve RAG pipelines, retrieval and document search. Extend LlamaIndex agents, workflows, retrievers and tool-calling capabilities. Integrate LLMs, APIs, databases and structured organisational data. Improve AI answer quality, citations, performance, security and reliability. Deliver well-tested, documented code and support technical handover. Key Requirement ...