24 of 24 Contract Retrieval-Augmented Generation Jobs in the UK

level expertise to join our dynamic team. Your primary focus will be on scaling AI assets and developing our innovative Retrieval-Augmented Generation (RAG) product. This role will place you at the intersection of advanced Large Language Models (LLMs), intelligent agents, and application development, contributing to the next generation of AI-driven … development with a strong focus on Python (backend) and React (frontend). In-depth knowledge of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and related AI/ML concepts. Demonstrated ability to design scalable, reliable, and maintainable software solutions. Strong team collaboration skills, with a proactive approach to problem-solving. Hands-on expertise … Python Experienced with REACT.js Familiar with Node.js Knowledge of Docker Understanding of LangChain Experience with cloud platforms such as Amazon Web Services (AWS) or Azure Familiarity with LLMs and RAG technologies Candidates will need to show evidence of the above in their CV in order to be considered. If you feel you have the skills and experience and want to More ❯

as advanced chatbots, summarization tools, document Q&A systems, and code assistants. Advanced Techniques: Apply sophisticated techniques like Prompt Engineering , Retrieval-Augmented Generation (RAG) , and context-aware pipelines to maximize model accuracy and relevance. Integration: Seamlessly integrate deployed AI models with existing enterprise systems, APIs, and data stores using back-end languages like Python … Data Engineering for Generative AI: Experience in preparing and curating diverse training datasets (structured/unstructured text, images, code). Deep knowledge of data preprocessing, tokenization, and embedding generation techniques. Hands-on experience working with Vector Databases (e.g., Pinecone, Weaviate, FAISS, Chroma) for semantic retrieval use cases. Stakeholder & Strategic Partnership: Ability to partner effectively with business More ❯

as advanced chatbots, summarization tools, document Q&A systems, and code assistants. Advanced Techniques: Apply sophisticated techniques like Prompt Engineering , Retrieval-Augmented Generation (RAG) , and context-aware pipelines to maximize model accuracy and relevance. Integration: Seamlessly integrate deployed AI models with existing enterprise systems, APIs, and data stores using back-end languages like Python … Data Engineering for Generative AI: Experience in preparing and curating diverse training datasets (structured/unstructured text, images, code). Deep knowledge of data preprocessing, tokenization, and embedding generation techniques. Hands-on experience working with Vector Databases (e.g., Pinecone, Weaviate, FAISS, Chroma) for semantic retrieval use cases. Stakeholder & Strategic Partnership: Ability to partner effectively with business More ❯

Foundry and Microsoft Copilot Studio. Proficiency in Python and familiarity with machine learning frameworks such as TensorFlow, PyTorch, and scikit-learn. Experience with Large Language Models, prompt engineering, and RAG implementations. Strong skills in data analytics, API development, and MLOps practices including CI/CD for ML. Excellent technical documentation and communication skills. Desirable knowledge in Docker, Kubernetes, and understanding More ❯

practises, including metadata tagging, version control, and retention policies. - Familiarity with AI integration workflows, including semantic indexing, vector databases, and retrieval-augmented generation (RAG). - Knowledge of Microsoft Graph API, Azure AI Foundry, and Copilot integration is a strong plus. - Experience with Filament, LlamaIndex, or similar AI connectors. - Familiarity with enterprise-grade security protocols More ❯

ReAct, Tree-of-Thoughts, and more. Deploy AI/ML pipelines using Azure ML, AWS SageMaker, Vertex AI, or Databricks. Integrate LLMs into production apps using LangChain, LlamaIndex, and RAG architectures. Build APIs and microservices for scalable AI deployment. Use AI-powered dev tools like GitHub Copilot, Cursor, and Codeium to speed up iteration. Apply MLOps/LLMOps practices with More ❯

Design, develop, and refine prompts to maximize the accuracy and effectiveness of GenAI models. Utilize techniques like few-shot prompting, chain-of-thought, and RAG (Retrieval Augmented Generation) to improve model performance within banking applications. Iteratively test and refine prompts based on the evaluation of AI outputs to enhance model performance. Manage the full … Profile Essential Skills/Knowledge/Experience: Strong understanding of Large Language Models (LLMs), including architectures, capabilities, and limits. Familiarity with different GenAI model types, such as text generation, summarization, and question answering. Knowledge of model hallucinations, bias, and context … windows. Mastery of prompting strategies such as zero-shot, few-shot, chain-of-thought (CoT), tree-of-thought (ToT), and self-consistency. Expertise in Retrieval Augmented Generation (RAG) architecture and implementation to integrate external, up-to-date, and proprietary data sources. Knowledge of prompt templating, variable injection, and dynamic prompt generation. Strong SQL skills More ❯

AI Engineers x 2 + fully remote contract + initially 6 months + £500 to £525 per day - Inside IR35 Key Skills: + Design of Gen AI Models + RAG + AI/ML Pipelines The Role: + Design, prototype, and deploy Generative AI models (LLMs, Transformers, Diffusion models) for enterprise use … cases. + Build and fine-tune LLM-based applications (chatbots, summarization, document Q&A, report generation, code assistants, etc.). + Apply prompt engineering, RAG (Retrieval-Augmented Generation), and context-aware pipelines to ensure accuracy and relevance. + Integrate AI models with enterprise systems, APIs, and data stores using Python, Java, or … . Ensure compliance with AI ethics, security, and governance standards. Prepare and curate training datasets (structured/unstructured text, images, code). Apply data preprocessing, tokenization, and embedding generation techniques. Work with vector databases (Pinecone, Weaviate, FAISS, Chroma) for semantic retrieval use cases. Partner with business stakeholders to identify and shape AI use cases. Contribute to More ❯

AI Engineers x 2 + fully remote contract + initially 6 months + £500 to £530 per day - Inside IR35 Key Skills: + Design of Gen AI Models + RAG + AI/ML Pipelines The Role: + Design, prototype, and deploy Generative AI models (LLMs, Transformers, Diffusion models) for enterprise use … cases. + Build and fine-tune LLM-based applications (chatbots, summarization, document Q&A, report generation, code assistants, etc.). + Apply prompt engineering, RAG (Retrieval-Augmented Generation), and context-aware pipelines to ensure accuracy and relevance. + Integrate AI models with enterprise systems, APIs, and data stores using Python, Java, or … . Ensure compliance with AI ethics, security, and governance standards. Prepare and curate training datasets (structured/unstructured text, images, code). Apply data preprocessing, tokenization, and embedding generation techniques. Work with vector databases (Pinecone, Weaviate, FAISS, Chroma) for semantic retrieval use cases. Partner with business stakeholders to identify and shape AI use cases. Contribute to More ❯

enterprise use cases. Build and fine-tune LLM-based applications (chatbots, summarization, document Q&A, report generation, code assistants, etc.). Apply prompt engineering, RAG (Retrieval-Augmented Generation), and context-aware pipelines to ensure accuracy and relevance. Integrate AI models with enterprise systems, APIs, and data stores using Python, Java, or Node.js … . Ensure compliance with AI ethics, security, and governance standards. Prepare and curate training datasets (structured/unstructured text, images, code). Apply data preprocessing, tokenization, and embedding generation techniques. Work with vector databases (Pinecone, Weaviate, FAISS, Chroma) for semantic retrieval use cases. Partner with business stakeholders to identify and shape AI use cases. Contribute to More ❯

and Generative AI R&D. Strong understanding of machine learning, data modelling , and natural language processing (NLP) techniques. Experience with fine-tuning , prompt orchestration , and retrieval methods (RAG, knowledge graphs). Familiarity with frameworks such as LangGraph , Azure AI Foundry Agents , and Semantic Kernel Agents . Good understanding of software engineering best practices , including version control, testing, and More ❯

Architect multi-step agent workflows using: Semantic Kernel SDK (C# or Python) Azure OpenAI (GPT-4, function calling, chat completion) Planner and Kernel Memory APIs for reasoning and memory RAG pipelines grounded in enterprise data via Azure AI Search Enterprise Data & AI Services Integration: Azure AI Search (vector indexing, hybrid search) Azure Form Recognizer for document understanding Azure Language Services More ❯

experience building and deploying machine learning models in a production environment. Strong programming skills and deep expertise in Python. Hands-on experience building with agentic or RAG (Retrieval-Augmented Generation) frameworks like LangChain or LlamaIndex. Familiarity with tools for working with Large Language Models via API or in a local context (e.g. HuggingFace transformers More ❯

experience building and deploying machine learning models in a production environment. Strong programming skills and deep expertise in Python. Hands-on experience building with agentic or RAG (Retrieval-Augmented Generation) frameworks like LangChain or LlamaIndex. Familiarity with tools for working with Large Language Models via API or in a local context (e.g. HuggingFace transformers More ❯

have Azure and be an expert with R&D on generative AI techniques Practical experience with GenAI techniques such as Finetuning, Prompt engineering, prompt orchestration, retrieval methods (RAG and Knowledge graph techniques), Agentic Systems etc. Knowledge of Agentic frameworks such as LangGraph, Azure AI Foundry Agents, Semantic Kernel Agents etc. Knowledge of prompt orchestration and optimisation techniques such More ❯

Create and maintain technical documentation Communicate complex concepts to all stakeholders. At least 3 years of experience in AI solution engineering. Large Language Models experience including prompt engineering and RAG implementations. Expert data analytics, MLOps practices and API development. Desirable knowledge in Docker and Kubernetes More ❯

with Google Cloud Run and Kubernetes (GKE) . Familiarity with GCP data tools like BigQuery and Google Cloud Storage (GCS) . Experience building complex agentic AI applications (beyond basic RAG or LangChain implementations). How We Evaluate Candidates Our interview process is designed to identify practical engineering competence and collaborative skills. Technical Acumen: The technical assessment is rigorous. We evaluate More ❯

public and private sector clients. Details- Proven experience building Agentic AI systems (e.g. autonomous agents, multi-agent orchestration, tool use, memory, planning) Strong hands-on skills in Python, LLMs, RAG, and LangChain or similar frameworks Deep understanding of GCP services: Vertex AI, BigQuery, Cloud Functions, Pub/Sub, etc. Experience with batch and real-time data pipelines Familiarity with AI More ❯

to public and private sector clients.Details- Proven experience building Agentic AI systems (e.g. autonomous agents, multi-agent orchestration, tool use, memory, planning) Strong hands-on skills in Python, LLMs, RAG, and LangChain or similar frameworks Deep understanding of GCP services: Vertex AI, BigQuery, Cloud Functions, Pub/Sub, etc. Experience with batch and real-time data pipelines Familiarity with AI More ❯

teams to align requirements for application development within a graph and semantic framework. Contribute to data modelling and architecture to support reporting, UI development, and AI-driven tools (LLMs, RAG queries, etc.). Work within an Agile delivery framework to drive business value and measurable impact. Develop and present business-impacting deliverables to senior stakeholders and executive leadership. Track adoption More ❯

hands-on experience in API design and cloud architecture (Azure). Experience with Excel add-ins or Office JavaScript APIs is highly desirable. Exposure to vectorization, RAG (Retrieval-Augmented Generation), or AI-driven data handling frameworks is a big plus. Bonus: Background or interest in commercial real estate technology. Self-starter with excellent communication More ❯

hands-on experience in API design and cloud architecture (Azure). Experience with Excel add-ins or Office JavaScript APIs is highly desirable. Exposure to vectorization, RAG (Retrieval-Augmented Generation), or AI-driven data handling frameworks is a big plus. Bonus: Background or interest in commercial real estate technology. Self-starter with excellent communication More ❯

DevOps Working closely with platform leads, architects, and SRE teams to ensure stable, scalable operations Supporting benchmarking, evaluation, and experiment tracking to measure LLM performance and cost Contributing to RAG implementations and vector-driven retrieval patterns Helping shape platform patterns, reusable components, and clear documentation Troubleshooting performance issues across distributed systems and cloud services What You’ll Bring … S3, SQS, DynamoDB, Bedrock RESTful API development with FastAPI, microservices, Terraform, GitOps workflows Prompt evaluation tools such as Promptfoo SQL and NoSQL experience: MySQL, PostgreSQL, MongoDB, Cassandra Exposure to RAG patterns and vector search technologies What Success Looks Like: Secure, reusable GenAI components running smoothly in production Faster engineering delivery through automation and DevOps maturity High observability and strong evaluation More ❯

user-focused AI services across our business. What You'll Do Design and implement a comprehensive AI 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 … LLM behaviour (accuracy, hallucination, bias, tone, etc.). Familiarity with tools like Trulens, HumanLoop, PromptLayer, or similar; experience designing QA approaches for GenAI environments. Knowledge of modern AI architectures (RAG pipelines, embeddings, API integrations such as OpenAI, Azure OpenAI, Anthropic). Experience designing and implementing structured test regimes in fast-evolving contexts. Excellent communication and facilitation skills, engaging both technical More ❯