12 of 12 Permanent Multi-Agent System Jobs in London

intelligent workflows for regulated use cases Develop automation-first AI pipelines for regulatory processes (e.g. monitoring, reporting, compliance checks) Implement multi-agent systems using modern orchestration frameworks (e.g. LangGraph or similar) Build and productionise machine learning models for classification, extraction, prediction … Exposure to computer vision or multimodal AI systems Knowledge of real-time data processing and streaming architectures Experience with multi-agent systems or intelligent agents in production Background in hybrid AI design (rules + ML + generative AI) What ...

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 ...

spike or proof of concept. What You’ll Be Doing Agentic AI & LLM Engineering Agentic Workflow Design: Develop multi-agent systems using frameworks like LangGraph or CrewAI for autonomous research and automated coding. Advanced RAG & Memory: Build sophisticated Retrieval-Augmented Generation … experience. Software Development & Technical Leadership Design and implement complex, scalable, and secure applications. Develop the architecture and ensure adherence to best practices. Optimize system performance and troubleshoot critical issues. Write clean, efficient, and maintainable code in Python, Java, and other high-level languages. Advocate for automation, testing ...

for insurance clients, including: LLM-powered applications for claims handling, underwriting support, policy servicing, document processing and customer operations Multi-agent architectures for insurance workflows, including triage, decision support, escalation, delegation and human-in-the-loop controls Retrieval and vector-based … applied data engineering Strong hands-on experience with LLMs, embeddings, RAG pipelines and vector databases Experience designing or implementing multi-agent systems or tool-calling frameworks Strong Python skills with experience building production-grade, regulated systems Experience with at least ...

integrating third-party data, research, or AI vendors. 15+ years in investment management workflows. Knowledge of advanced RAG and multi-agent systems. Relevant certifications (Databricks GenAI, SnowPro GenAI, AWS ML). CFA charterholder or active candidate. ...

for insurance clients, including: LLM-powered applications for claims handling, underwriting support, policy servicing, document processing and customer operations Multi-agent architectures for insurance workflows, including triage, decision support, escalation, delegation and human-in-the-loop controls Retrieval and vector-based … applied data engineering Strong hands-on experience with LLMs, embeddings, RAG pipelines and vector databases Experience designing or implementing multi-agent systems or tool-calling frameworks Strong Python skills with experience building production-grade, regulated systems Experience with at least ...

behind Revax’s AI-native platform for professional services. You’ll design, optimise, and scale the systems that power multi-agent drafting, knowledge graphs, and auditable AI workflows used by accountants, tax advisors, and consultants at leading firms. This … real-world data · Design and implement APIs using FastAPI for AI workflows and product features · Build and scale LangGraph-based multi-agent systems with checkpointing, retries, and observability · Integrate and scale vector search, knowledge graphs (Neo4j), and associated retrieval pipelines into ...

frameworks. • Understanding of AI lifecycle: prompt engineering, agent workflows, deployment, and monitoring. • Familiarity with LLMs and multi-agent systems. About Us: Ascendion is a leading provider of AI-first software engineering services. Our applied AI, software engineering, cloud ...

technical environment. Expertise in AI and Machine Learning, including agent-based AI, RAG (Retrieval Augmented Generation), multi-agent systems and conversational agents. Strong programming skills in Python, Java or .NET. Experience with GenAI and LLMs (e.g. ChatGPT ...

outside of simulation. The team is highly technical and collaborative, so you’ll be involved not just in development, but also in shaping system architecture and contributing to longer-term technical direction. Key Responsibilities Develop probabilistic and machine learning models for decision-making and control Build and refine … methods or reinforcement learning Desirable: Experience working with robotic systems or autonomous platforms Familiarity with SLAM, path planning or multi-agent systems Knowledge of ROS/ROS2 or robotics simulation tools Understanding of control systems and sensor fusion Experience ...

building the next generation of autonomous AI for Client Services. This isn't another LLM wrapper. Our client is designing multi-agent systems that genuinely operate inside complex enterprise organizations, understand rich context, and take real-world action. With a freshly … environment where your early architectural decisions will define the product for the next 3–5 years. Core technical hurdles include: Multi-Agent Orchestration: Designing a "Master Agent" to route tasks to specialized sub-agents. Persistent Memory: Engineering systems ...

Github Copilot Coding Agents or similar) Desirable: Experience with prompt engineering, Retrieval-Augmented Generation (RAG), and graph databases Familiarity with multi-agent LLM systems and agentic platforms (e.g., AutoGen, CrewAI), and experience deploying LLM-based applications Experience with tools such … Success Metrics Deploy secure, scalable, and maintainable full-stack systems and LLM applications that deliver measurable business value Maintain low latency, high system uptime, and strong performance across APIs and AI services Drive fast, iterative collaboration across product, design, and engineering teams Continuously improve the platform through ...