14 of 14 Retrieval-Augmented Generation Jobs in Central London

varied use cases. Build agentic workflows and reasoning pipelines using frameworks such as LangChain, LangGraph, CrewAI, Autogen, and LangFlow. Implement retrieval-augmented generation (RAG) pipelines using vector databases like Pinecone, FAISS, Chroma, or PostgreSQL. Fine-tune prompts to optimise performance, reliability, and alignment. Design and implement memory modules for short-term and long-term … cloud AI tools, observability platforms, and performance optimisation. This is an opportunity to work at the forefront of AI innovation, where your work will directly shape how next-generation systems interact, reason, and assist. More ❯

driven architectures tailored to finance-specific use cases, including: Intelligent document processing (KYC/AML) Conversational finance assistants (customer service, advisory) Automated risk and compliance workflows Synthetic data generation for testing and modeling Personalized financial insights and reporting Select the right GenAI technologies (open-source, proprietary, cloud, or hybrid) to meet client goals without being tied to a … stakeholders in both business and technology. Experience working in or with regulated financial environments and navigating security and compliance requirements. Preferred Qualifications Experience with retrieval augmented generation (RAG), fine-tuning, model evaluation, or deploying models in production environments. Understanding of financial risk modeling, model validation, or operational risk frameworks. Knowledge of regulatory frameworks such More ❯

secure cloud development practices and IAM role design. · Understanding of LLM fine-tuning, embeddings, vector stores (e.g., Pinecone, FAISS, OpenSearch). · Exposure to contact centre automation, conversational agents, or RAG pipelines. Please click here to find out more about our Key Information Documents. Please note that the documents provided contain generic information. If we are successful in finding you an More ❯

tools for modelling. Working experience on Modern data platforms which involves Cloud & related technologies Keeps track of industry trends and incorporates new concepts Advanced understanding of AI concepts , LLMS, RAG, Agentic apps Advance Understanding in Data visualization and Data pipelines. Excellent understanding of traditional and distributed computing paradigm. Experience in designing and building scalable data pipelines. Should have excellent knowledge More ❯

and be able to make sense of ambiguous problem statements. Our client problems can range in a variety of domains. Some examples, but not limited to, are building a RAG leveraging open source or commercial LLMs, building a Multiagent system, leveraging Small Language models that could be locally resident, problems in computer vision, speech, Natural Language Processing (NLP), multilingual models 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 Microsoft 365 & Graph API Integration Enable agents to access and reason over content in: SharePoint, OneDrive, Teams, Outlook, and Planner Use More ❯

work on fine-tuning, integrating, and scaling LLMs for real-world applications. Key Skills: Strong Python engineering background Experience with LLMs (e.g. Hugging Face, OpenAI, LangChain) Model fine-tuning, RAG pipelines, vector databases (e.g. FAISS, Pinecone) Cloud (AWS/GCP), CI/CD, Docker Bonus: Knowledge of model optimization, quantization, or open-source contributions. 📩 If interested send your CV to More ❯

work on fine-tuning, integrating, and scaling LLMs for real-world applications. Key Skills: Strong Python engineering background Experience with LLMs (e.g. Hugging Face, OpenAI, LangChain) Model fine-tuning, RAG pipelines, vector databases (e.g. FAISS, Pinecone) Cloud (AWS/GCP), CI/CD, Docker Bonus: Knowledge of model optimization, quantization, or open-source contributions. 📩 If interested send your CV to More ❯

What We’re Looking For Strong experience in software engineering (preferably 5+ years) Proficiency with Python, data processing, microservices, and distributed systems Experience working with Large Language Models (LLMs), RAG pipelines, or similar AI tooling Comfortable owning technical delivery and leading small teams Strong communication skills - able to engage with both technical and non-technical stakeholders Ability to manage multiple More ❯

and wants to shape how AI is used in the physical world. 🧠 You’ll need: 2+ years' engineering experience with a builder’s mindset Hands-on with LLMs — LangChain, RAG, agents, fine-tuning, etc. Infra knowledge (cloud, containers, relational/graph DBs) Bonus: startup/founder experience 🔧 You’ll be doing: Shipping to prod from Day 1 Building end-to More ❯

and wants to shape how AI is used in the physical world. 🧠 You’ll need: 2+ years' engineering experience with a builder’s mindset Hands-on with LLMs — LangChain, RAG, agents, fine-tuning, etc. Infra knowledge (cloud, containers, relational/graph DBs) Bonus: startup/founder experience 🔧 You’ll be doing: Shipping to prod from Day 1 Building end-to More ❯

support secure, air-gapped AI deployments, with a focus on NLP-based tooling * Develop pipelines for transcription ingestion and real-time analytical insight generation * Support graph and RAG-based inference layers using data from structured and unstructured sources * Build and expose APIs for frontend consumption, enabling natural-language querying, dynamic visualisation, and reporting * Ensure system portability via containerisation More ❯

Doing: Architecting and implementing secure backend services to support AI deployments in classified settings Developing transcription ingestion pipelines and real-time insight generation capabilities Supporting graph and RAG-based inference pipelines using structured and unstructured data Exposing robust APIs for frontend engineers to deliver interactive dashboards and NLP-driven workflows Ensuring system portability via containerisation (Kubernetes, Docker) Collaborating … of Postgres or similar databases Proven experience building real-time or batch AI/ML pipelines with strong API design (Bonus) Exposure to LLMs, vector databases, transcription pipelines, or RAG systems (Bonus) Prior work in Defence, aerospace, or national security environments Why This Project? This isn’t another generic SaaS deployment. You’ll be building backend systems that enable critical More ❯

Scientist into their AI Research team, focusing on LLMs, RAGs, Agent-based systems and multimodal AI. Responsibilities: Lead the technical design and implementation of sophisticated LLM-based systems, including RAG, agent-based architectures, and multimodal AI solutions. Oversee the lifecycle of LLM projects, from model pre-training and fine-tuning to evaluation and deployment, ensuring alignment with advanced use cases. …/ML Exp. developing, fine-tuning, and deploying LLMs. Solving algo problems from end-to-end Exp. preparing data, then training models on GPUs Proficient in advanced methodologies like RAG and agent systems, keeping up to date with latest tech, papers, and understanding the theory behind advanced models. Expertise in frameworks such as PyTorch, TensorFlow, and Hugging Face. Strong understanding More ❯