1 to 25 of 63 Permanent Multi-Agent System Jobs in the UK excluding London

role sits at the intersection of systems architecture, agentic AI workflows, and customer-facing problem solving. You'll design multi-agent systems, build reusable primitives, and convert complex financial workflows into scalable automated products. You'll work directly with leading … deployment, and scale. What You'll Do Take ambiguous workflow requests and turn them into scoped, architected, implemented, and deployed multi-agent systems Build reliable multi-step, multi-agent ...

Lambda, Step Functions). Build CI/CD pipelines for ML models, agents, and GenAI applications. Deploy LLMs and orchestrate multi-agent systems (LangChain, LangGraph, or custom). Create and maintain data pipelines (Airflow, dbt, Step Functions). Implement monitoring, observability … . Experience with MLflow , CI/CD tools, and automated testing. Hands-on with LLM deployment and multi-agent systems . Proven experience building data pipelines and production ML workflows. Strong grounding in software engineering best practices and cost optimisation. Nice ...

risk in financial terms (£X exposure), map behaviours to regulatory requirements, and detect cascade failures before they propagate through multi-agent systems • Protocol Integration: Implement monitoring for agent communication protocols (Model Context Protocol, Agent2Agent, Agent … through first principles • You communicate technical concepts clearly to non-technical stakeholders Highly Valued (Differentiated Candidates) • Publications or research in multi-agent systems, reinforcement learning, AI safety, or agent architectures • Experience at AI labs (Anthropic, OpenAI, DeepMind ...

Build & Own AI Systems Design and ship LLM applications using modern orchestration, prompt frameworks, and evaluation loops Build multi-agent systems (planning, tool use, safety constraints, monitoring) Implement retrieval and vector-based architectures (RAG, embeddings, semantic workflows) Apply ontology … applied data engineering Strong hands-on experience with LLMs, RAG, vector stores, and embeddings Experience building or orchestrating multi-agent systems Strong Python skills and ability to ship production-grade code Experience with at least one major AI cloud ecosystem ...

Lead, owning the technical vision and AI architecture for the engagement Design and oversee GenAI and Agentic AI solutions, including multi-agent systems, orchestration, and evaluation frameworks Guide the use of LLMs, ML models, and scenario-modelling techniques to support pricing … Generative AI and Agentic AI Proven experience designing and delivering enterprise-scale AI architectures Strong hands-on experience with LLMs, multi-agent systems, and ML pipelines Cloud expertise across GCP and/or Azure (Vertex AI, Azure AI, ML platforms, APIs ...

existing enterprise stack. Conversant with end-to-end Generative and Agentic AI solutions for enterprise use cases. Design familiarity with multi-agent systems capable of reasoning, planning, and executing tasks autonomously. Evaluate and select appropriate models, frameworks, and orchestration tools. Ability ...

/ML engineer with real deployments, excellent communication skills and a passion for teaching. Required experience: Previously built and deployed multi-agent systems end-to-end Strong hands-on expertise with LangGraph Experience with knowledge graphs, RAG and LLM tool orchestration ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...

User-Defined Agent Logic: Creating a \"no-code\" engine where users can verbally define workflows and guardrails that the system executes deterministically. Hierarchical & Auditable RAG: Routing queries through complex layers of patient history, clinical guidelines, and organizational policies with full traceability. Resilient Orchestration: Managing … architecture and evolution of the \"Central Brain\" the core service that powers our AI agents. You will design multi-agent systems that reason, retrieve data, and communicate via voice and text in real time. Key Responsibilities: End-to-End Ownership: Define ...