10 of 10 Contract LangChain Jobs in the UK excluding London

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-style models, sentiment analysis) Experience integrating vector databases (e.g. Azure AI Search, OpenSearch, Pinecone, Weaviate ...

Deployment Model Deployment: Flask, FastAPI, MLflow Model Serving: Triton Inference Server, Hugging Face Inference Endpoints API Integration: OpenAI, Anthropic, Cohere, Mistral APIs LLM Frameworks: LangChain, 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 ...

Experience Strong hands-on experience 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 ...

Skills & Experience Strong proficiency in Python for AI/ML 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 ...

Application Architecture Tech Stack: Deep expertise in Google Cloud Platform (GCP) , Vertex AI , and Gemini Models . AI Frameworks: Strong hands-on experience with LangChain , Vector Databases (Pinecone, Weaviate, etc.), and LLMOps tools. Domain: Experience delivering AI/GenAI use cases within Banking or highly regulated industries is a significant ...

full lifecycle (discovery prototyping hardening production monitoring continuous improvement) of GenAI and agentic systems. LLM orchestration & tooling: Design and implement workflows using LangChain, LangGraph, LlamaIndex, Semantic Kernel or similar. Optimize prompt strategies, memory, tools, and policies. RAG & vector search: Architect robust RAG pipelines with vector DBs (Pinecone, Chroma, Weaviate, pgvector … including production deployments. Strong system design and scalable architecture skills for AI-first applications and platforms. Hands-on expertise with LLM orchestration frameworks (e.g.,LangChain/LangGraph/LlamaIndex/Semantic Kernel). Proven experience with RAG and vector databases (e.g., Pinecone, Chroma, Weaviate, pgvector). Proficiency in Python (primary ...

Full Stack AI Engineer (Agentic AI & LangChain) - Contract Duration: 3 Months Rate: Up to £700 per day (Inside IR35) Location: Hybrid - Oxford We are seeking an experienced Full Stack AI Engineer to join a growing tech company on an initial 3-month contract. This role is ideal for someone with … strong, hands-on experience building agentic AI systems , particularly using LangChain , and who enjoys working in fast-paced, product-led environments. The Role You will play a key role in designing, building, and deploying AI-powered products, working closely with cross-functional teams to deliver intelligent, scalable solutions. Key responsibilities ...

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 (e.g., FAISS, Pinecone, Weaviate, Milvus) for fast similarity search and retrieval. Develop embedding pipelines … Knowledge of popular vector DBs: Pinecone, Weaviate, FAISS, Vespa, Milvus. Generating and managing embeddings (using models like SentenceTransformers, OpenAI, Hugging Face). Familiarity with LangChain for building LLM-powered applications. Ability to create chains, prompts, and agents. Desirable Skills/Knowledge/Experience Experience with data ingestion, indexing, and querying. ...

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) Collaborating with Data Science & Engineering teams to productionise models What … 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 experience Please note: This role does not provide sponsorship ...

frameworks and cloud-native technologies. Key Responsibilities Design and develop AI-driven applications using LLMs and agent-based architectures Build and integrate workflows using LangChain and/or LangGraph Develop robust backend services using Python Contribute to frontend or full-stack development using JavaScript/TypeScript where required Deploy, scale … cleared environments Required Skills & Experience Strong commercial experience as a Software Engineer working with AI/LLM-based systems Hands-on experience with LangChain and/or LangGraph Excellent Python development skills Solid experience with JavaScript and TypeScript Proven experience deploying applications on AWS Strong understanding of software architecture, APIs ...