14 of 14 Contract Retrieval-Augmented Generation Jobs in the South East

solutions that sit at the heart of real business workflows. This is a hands-on contract role suited to someone who has delivered RAG pipelines, multi-agent systems and NLP-driven applications in live environments, ideally within complex or regulated domains. Location: London (2 days onsite) Contract: 6 Months (OIR35 … Python experience for ML and AI development Hands-on experience with LLMs & Generative AI , including: Retrieval-Augmented Generation (RAG) Prompt & context engineering Agentic/multi-agent architectures Experience with frameworks such as LangChain, LangGraph, LangSmith or similar Solid NLP background (tokenisation, embeddings, transformers, BERT ...

services, APIs and integrations with existing platforms Implement data pipelines, embeddings, vector search and retrieval-augmented generation (RAG) patterns Work closely with engineering, product and business stakeholders to shape AI use cases Ensure solutions meet security, governance and performance requirements Contribute to best practice … with vector databases, embeddings and modern AI architectures Comfortable working in agile, fast-moving delivery environments Nice to Have Experience with GenAI use cases (RAG, agents, copilots, document automation) Exposure to MLOps , CI/CD and monitoring of AI systems Experience in regulated or enterprise environments Consulting or client-facing ...

LlamaIndex for building LLM-powered applications Vector Databases: FAISS, Weaviate, Pinecone, Qdrant (Nice-to-Have) Retrieval-Augmented Generation (RAG): Experience building hybrid systems combining LLMs with enterprise data MLOps & Infrastructure MLOps: Model versioning, monitoring, logging Bias Detection & Mitigation Content Filtering & Moderation Explainability & Transparency ...

ideal for someone who excels at technical storytelling and enjoys translating complex concepts-such as retrieval-augmented generation (RAG), vector search, and large language model (LLM) integrations-into engaging, developer-focused multimedia content. You will play a key role in shaping video strategy, producing … curate a content calendar with a strong focus on video and demo assets Script, produce, and edit technical videos (e.g. step-by-step RAG demos, vector search walkthroughs, LLM integration tutorials) using tools such as Camtasia or similar Collaborate closely with engineers, developer advocates, and demo creators to ensure technical ...

artificial intelligence, and machine learning, with considerable in-depth knowledge in implementing solutions using AWS. Practical cloud-native experience, specifically with AWS. Experience with RAG-based semantic search and LLM inference workflows using OpenAI and Claude models. ...

observability). Demonstrated success in leading teams Deep understanding of AI/ML solutions implementation, with emphasis on LLM applications and retrieval-augmented generation. Expertise in modern SDLC and DevOps: CI/CD (e.g., Jenkins/GitLab), infrastructure as code (e.g., Terraform/CloudFormation), automated testing ...

TypeScript-based applications Understanding of semantic/graph data (e.g., RDF triples, SPARQL , Amazon Neptune ) Ability to validate AI-supported features, including LLM/RAG behaviours via Amazon Bedrock Knowledge of performance testing for serverless architectures and WCAG 2.2 AA accessibility Familiarity with GDS Standards and testing in the public ...

solutions that improve operational efficiency, regulatory compliance, and customer trust while leveraging advanced analytics and automation. Your Responsibilities Design, develop, and optimize RAG-based solutions integrating retrieval systems with large language models. Build and maintain applications using LangChain to orchestrate complex AI workflows. Implement and manage vector databases … scalable AI-powered applications. Fine-tune and evaluate large language models for specific use cases and domain adaptation. Optimize retrieval and generation workflows for performance, accuracy, and cost-efficiency. Stay updated on the latest advancements in generative AI, retrieval techniques, and vector search technology. ...

Agentic AI solutions aligned to real business workflows Build and orchestrate autonomous agents with planning, reasoning, and tool use Develop LLM-driven systems including RAG, Q&A, and enterprise copilots Integrate GenAI into existing platforms, products, and processes Own delivery end-to-end: design through to production Work closely with … Generative AI and LLMs Agentic AI frameworks such as LangGraph, AutoGen, or CrewAI Python with modern AI libraries (LangChain, Hugging Face, PyTorch) Experience building RAG pipelines and knowledge retrieval systems Cloud platforms: Azure, AWS, or GCP Microsoft/Azure (Highly Desirable) Microsoft AI Foundry Azure AI Agent Service ...

that enhance global sales workflows. Build scalable backend services and full-stack applications for internal teams. Architect, implement, and optimize LLM orchestration frameworks and RAG-based solutions. Collaborate with cross-functional teams to define requirements and deliver innovative tools. Ensure reliability, scalability, and performance of distributed systems handling massive datasets. … workflows . Strong proficiency in Angular (primary frontend); React optional. Hands-on experience with LangChain, LangGraph, and Indexify , with a deep understanding of RAG architectures . Expert-level SQL and experience with BigQuery and vector databases (Pinecone, Weaviate, Vertex AI Search). Proven track record in MLOps and deploying ...

best practices for content analytics. Core Skills & Competencies . Technical Skills: o Experience or interest in NLP and LLM applications (transformers, Retrieval-Augmented Generation, prompt engineering) o Familiarity with data visualization and scientific communication tools o Knowledge graph and ontology management o Python ...

depth knowledge in implementing solutions using AWS. Deep understanding of AI/ML solutions implementation, with emphasis on LLM applications and retrieval-augmented generation. Practical cloud-native experience, specifically with AWS (compute, storage, networking, IAM, KMS, observability). Experience with RAG-based semantic search ...

months IR35: Outside Location: London (onsite once per month ) Start: ASAP What you’ll work on Building Agentic AI workflows and automation Designing RAG pipelines for insurance data Developing LLM-powered tools using Python , LangChain , LlamaIndex , and vector databases Evaluating, fine-tuning, and integrating LLMs (OpenAI/Anthropic/Mistral … Data Science & Engineering teams to productionise models What you’ll need Strong Data Science + AI Engineering background Hands-on experience with Agentic AI , RAG , LLMs , LangChain , Python Knowledge of vector search, embeddings, and scalable pipelines Experience working in enterprise or regulated environments Must have insurance domain experience Insurance domain ...

until at least February 2027. What you'll need to succeed Experience or strong interest in NLP, LLMs and AI applications such as transformers, RAG or prompt engineering, preferably gained within the pharmaceutical, biotech, medtech or biomedical space Familiarity with Python and modern AI frameworks for text analytics, alongside data … content, analytics, biomedical, literature, mining, summarisation, machine, learning, data, ontology, metadata, FAIR, knowledge, graphs, information, retrieval, Python, text, analytics, RAG, drug, discovery, development, transformers, semantic, technologies, visualisation, scientific, workflows, biopharma ...