76 to 98 of 98 Retrieval-Augmented Generation Jobs in London

done real AI work inside a high-calibre engineering organisation and worked closely with product. What you'll do Design and deploy LLM/RAG systems (GPT, Claude, Gemini) powering content generation, semantic search, and personalised learning experiences Build Knowledge Graph capabilities to underpin agentic workflows … Technically, you bring: Python fluency (NumPy, Pandas, Scikit-Learn, PyTorch) and solid TypeScript/API skills Hands-on experience with LLMs prompt engineering, evaluation, RAG architectures, safety considerations Cloud-native development on AWS and practical MLOps: CI/CD for models, version control, observability, retraining pipelines Familiarity with LangChain, Terraform ...

through cutting edge technology, AI and data driven solutions. This is an exciting opportunity to join a growing team focused on building next generation GenAI applications and scalable full stack solutions. The Role As a GenAI Full Stack Engineer, you will play a key role in designing, building … LangChain, LangGraph or CrewAI Experience working with Large Language Models such as OpenAI, Anthropic, Llama or Mistral Exposure to Retrieval Augmented Generation or AI agents is beneficial Experience with AWS or Azure Docker and containerisation experience, Kubernetes beneficial Experience with CI CD pipelines using ...

software engineering principles (Python preferred) Business-focused mindset, able to evaluate AI initiatives through an ROI lens Cloud and AI knowledge, including LLMs, RAG, prompt engineering, and modern AI tooling Solid Python knowledge Familiarity with Claude and similar frontier models Production experience using LangChain …/ML or similar discipline Desirable RAG architectures, embeddings, and vector databases Prompt management, evaluation, and observability Cloud deployment (AWS, Azure, or GCP) Enterprise concerns: security, governance, and cost control Strong stakeholder communication and technical decision-making ...

delivery of scalable, resilient AI/ML pipelines aligned to business goals. Build and deploy advanced ML, DL, and LLM solutions, including RAG, agentic architectures, and evaluation frameworks. Mentor engineers in ML engineering, orchestration, and modern AI best practices. Communicate system behaviours, risks, and outcomes to both technical … Partner with the Head of AI Labs to turn AI research and strategy into production‐ready solutions. Key Requirements: Proven experience designing and productionising RAG pipelines and agentic AI architectures Hands‐on delivery of agent‐based AI systems with orchestration tools (e.g., LangChain, CrewAI) in production. Strong Python engineering skills ...

environment where experimentation, iteration, and innovation are actively encouraged. What You’ll Be Doing Designing and building production-grade AI systems using LLMs Developing RAG pipelines, vector search solutions, and agent-based workflows Creating robust evaluation frameworks to measure accuracy, reliability, and performance Building scalable APIs, services, and data pipelines … What We’re Looking For Experience building applications using LLM APIs, with a strong understanding of their strengths and limitations Hands-on experience with RAG architectures, vector databases, and prompt engineering Experience developing multi-step workflows or agentic systems (frameworks or custom builds) Strong programming skills (Python or similar), with ...

lasting around nine months, building AI applications that solve real operational problems. Key Responsibilities • Design and implement LLM-powered applications for enterprise clients • Build RAG pipelines and AI workflows integrating enterprise data • Develop production APIs and backend services in Python • Implement evaluation frameworks and monitoring for AI systems • Optimise … squads Key Details • Salary: £75,000 – £90,000 • Working model: Hybrid (2–3 days per week in Central London) • Tech stack: Python, LLM APIs, RAG architectures, vector databases, agent frameworks, cloud platforms (AWS/GCP/Azure) • Visa sponsorship: Not available Interested? Please apply below. ...

Technical Skills Required Proven experience of: Agent Orchestration: LangChain, LangGraph, CrewAI - not just conceptual Agentic Coding Tools: Claude Code CLI, Cursor, OpenAI Codex, Copilot RAG & Vector Stores: Chroma, Weaviate, Pinecone, know where RAG breaks LLM APIs & SDKs: Anthropic, OpenAI, Gemini - prompt design, tool use Python/TypeScript: Primary languages … agent orchestration with memory, tool routing, and state management Built projects where AI (Claude Code, Codex, Cursor) wrote significant portions of the code Implemented RAG pipelines end-to-end - chunking, embedding, retrieval, re-ranking, evaluation Integrated agents with real enterprise APIs - not just OpenAI playground or sample data ...

intent accounts, generate tailored content, and execute strategic plays. They are building AI-first features to make this seamless and intelligent, from content generation to account strategy recommendations. The Role My client is seeking a senior Applied AI Engineer to lead the development and deployment of novel applications … Prototype and ship AI-powered product capabilities across the platform — from content generation to account intelligence and campaign automation. Design and implement RAG pipelines using vector databases like Qdrant or Weaviate for contextual awareness and retrieval. Build robust backend services in TypeScript to serve AI-driven features, including ...

semantic search and information retrieval. Knowledge of effective text chunking techniques for optimal processing and indexing of large documents or datasets. Expertise with RAG concepts and fundamentals (vectorDBs, semanticsearch, re‐rankers etc.), Expertise in implementing RAG systems that combine knowledge bases. Experience with multi‐agent frameworks/systems ...

deployment. Build MVPs and collaborate closely with Engineering and Product teams to bring ideas to life. Apply advanced machine learning and LLM techniques, including RAG, agents and NLP, where they drive meaningful customer and product impact. Work with large-scale datasets in cloud environments to deliver robust, scalable systems. Contribute … end. Proficiency in Python and SQL, with experience working on cloud-scale datasets. Practical experience with LLMs and applied AI, such as RAG, agents, or NLP. Experience building customer-facing or product-centric ML systems. A product-focused mindset, balancing experimentation with real-world value. Useful additional experience includes ...

/B experiments and performance dashboards. • Integrate AI agent functionality with applications through MCP servers and reliable tool configurations. • Develop secure and scalable RAG pipelines, including ingestion, text processing, metadata handling and vector search in GCP. • Embed security, compliance, GDPR controls and best‐practice engineering with clear documentation and stakeholder … Strong Python skills for backend services, SDKs, API development, authentication and testing. • Hands‐on experience working with LLMs, embeddings, prompt engineering, tool calling and RAG design. • Practical knowledge of GCP services including Vertex AI, Model Garden, BigQuery, Cloud Run and Google’s ADK. • Experience with document and data processing using ...

equity & benefits Reports to: CTO Overview of the Role This is a rare opportunity to shape and lead the evolution of a next-generation, AI-native data platform within a high-growth, well-funded scale-up. As Director of Data Engineering, you will operate at the intersection … development of a knowledge graph and data enrichment pipelines to unlock proprietary data value Drive AI/ML Ops maturity , including LLM deployment, RAG pipelines, and evaluation frameworks Engineering & Architecture Define scalable, cloud-native architectures across GCP (preferred) and AWS Lead cross-cloud data orchestration , ensuring seamless data flow from ...

powered tools, systems and agents to streamline sourcing, research, diligence, and portfolio monitoring Design and deploy end-to-end LLM applications including research copilots, RAG systems, workflow automation, data enrichment, and deal intelligence tooling Ingest, clean, and analyse external datasets through scripts, pipelines, and lightweight ML components Integrate third-party … applied AI engineering, ML engineering, or forward deployed roles Strong Python Experience building and deploying LLM applications (OpenAI, Anthropic, Gemini, etc.) Deep familiarity with RAG methodologies, embeddings, and vector databases (Pinecone, Weaviate, pgvector) Robust API integration experience, including working with third-party datasets, web APIs, or scrapers A product mindset ...

powered tools, systems and agents to streamline sourcing, research, diligence, and portfolio monitoring Design and deploy end-to-end LLM applications including research copilots, RAG systems, workflow automation, data enrichment, and deal intelligence tooling Ingest, clean, and analyse external datasets through scripts, pipelines, and lightweight ML components Integrate third-party … applied AI engineering, ML engineering, or forward deployed roles Strong Python Experience building and deploying LLM applications (OpenAI, Anthropic, Gemini, etc.) Deep familiarity with RAG methodologies, embeddings, and vector databases (Pinecone, Weaviate, pgvector) Robust API integration experience, including working with third-party datasets, web APIs, or scrapers A product mindset ...

Experience Strong commercial experience using Python in applied AI or machine learning contexts Proven delivery of end-to-end AI solutions such as RAG systems, LLM-powered applications, or agent-based workflows Experience working closely with clients or end users, translating real requirements into technical solutions Solid software engineering fundamentals … including maintainable code, testing, and collaboration with engineering teams Practical knowledge of prompt engineering, RAG pipelines, agent workflows, and model evaluation Familiarity with modern GenAI tooling such as LangChain, LangGraph, or similar frameworks Motivation to work in a startup environment, with comfort around ambiguity, pace, and ownership What They Offer ...

GenAI workflows while working directly with users to shape how the product evolves. Key Responsibilities • Build end-to-end GenAI workflows using Python • Develop RAG pipelines and agent-based systems • Translate client requirements into production-ready solutions • Deliver POCs that evolve into scalable features • Collaborate with engineers on production deployment … Support demos and tailored client use cases Key Details • Salary: £65k–£90k • Working: Hybrid (3–4 days onsite, Holborn) • Stack: Python, LLMs, RAG, agents, LangChain/LangGraph • Visa: Cannot sponsor Interested? Please apply below. ...

/Claude Code) Strong Plus Experience building agentic workflows that are trusted Experience with LangChain, LangGraph, or similar Experience building with vector databases, embeddings, RAG pipelines Experience with graph databases Experience building simulation, optimisation, or decision-support systems Prior startup or early-stage experience Why Join Us Work on problems … sustainability and your experience of designing data models, architecting platforms and building from zero to one? What do you think about the latest generation of coding LLMs - good, bad, what have you used ...

Work closely with stakeholders - listening, probing, and shaping solutions around real needs. Essential Experience Experience automating human-centric processes (approvals, performance workflows, document generation, analytics, etc.). Proven experience building AI agents and multi-step automation flows. Strong hands-on engineering skills (clean, explainable, well-structured code). … Expertise using ChatGPT Enterprise for workflow automation. Skilled in designing prompts, guardrails, and evaluation logic for reliable outputs. Experience building retrieval pipelines (RAG), vector search, or context-aware systems. Comfortable integrating AI systems with APIs and internal platforms. How to Apply If you're an AI Engineer ...

join at the foundational stage, working directly with world‐class engineers and product leaders to build the backend systems behind a next‐generation AI lifestyle platform. This product is already in the hands of deeply engaged early users, with engagement metrics far above industry norms. You will play … delivery of key features—from design to production rollout. Develop background processing systems, task queues, and agent orchestration. Work hands‐on with LLM integrations, RAG pipelines, and AI‐driven systems. Enhance system performance across SQL queries, APIs, and distributed jobs. Build and operate cloud infrastructure on GCP. Lead debugging ...

build a high-conversion sales pipeline. Al Revenue Ownership: Own the full lifecycle of Al Maas opportunities in international markets, from lead generation and qualification to solution design, commercial negotiation, and deal closure, driving growth in token consumption and revenue. Market & GTM Strategy Support: Track GenAl trends (foundation … pricing, and contracting, while collaborating with solution architects and product teams Cloud Experience: Familiar with cloud and AI infrastructure products (e.g., servers, GPU, MaaS, RAG, Agents); hands-on experience in cloud sales, business consulting, and operations. Mindset: Fast learner, customer-obsessed, results-driven, self-motivated, and passionate about Al innovation ...

international scale. ✨ 6 reasons this role is remarkable Build the brain. You'll own the core AI agent infrastructure. Telephony, LLM orchestration, RAG pipelines, and the event-driven architecture that ties it all together. Be a founding engineer at an AI company rewriting a trillion-dollar industry. Property still runs … Architect and own the core Python backend powering our AI agents. Own the AI infrastructure. Build the telephony and voice layer, LLM orchestration, and RAG pipelines Ship rock-solid backend systems. Build robust API integrations with CRMs and property management systems. Design for scale. Build API-first, event-driven architectures ...

GenAI Engineer/Software Developer (Python LLM RAG) London 12 month FTC to £180k Are you a Senior Software Engineer with a strong knowledge of the capabilities of GenAI? You could be progressing your career in a hands-on role at a tech driven, global Asset Manager with multiple billions … team and work closely with Investment Analysts on a mix of prototyping, evaluation and engineering. The work is interesting and complex, spanning Python development, RAG and retrieval workflows, MCP and tool integrations, model evaluation and the engineering needed to turn promising ideas into reliable internal tools. ...

building the next generation of AI and autonomous agents that can reason, plan, act, and learn to solve critical problems in operations at the huge scale of the world’s largest bank. As an AI Product Manager at the Corporate and Investment Banking operations team, you will leverage … through execution and launch. Familiarity with AI model architectures, such as Large Language Models, and methods such as prompting, context engineering, fine-tuning, RAG, MCPs, and agentic frameworks. Preferred qualifications Advanced degree in Computer Science, engineering, or related field. Experience defining robust evaluation sets and leading teams through quantitative ...