22 of 22 Remote/Hybrid Multi-Agent System Jobs in London

Responsibilities Design and deliver enterprise-scale Agentic AI and Generative AI solutions Lead the architecture and implementation of autonomous and multi-agent systems Design AI-powered assistants, intelligent workflows and RAG-based solutions Collaborate with business and technology teams to integrate … grade AI solutions on AWS Strong knowledge of AWS Bedrock, Lambda, Step Functions and related services Experience designing AI agents, multi-agent systems and intelligent workflow automation Hands-on experience with RAG architecture and AI-powered assistants Knowledge of LangGraph ...

knowledge management, and workflow automation. Architect advanced retrieval using RAG, Agentic RAG, Graph RAG, knowledge-graph, and hybrid approaches. Design multi-agent systems with modern orchestration and reasoning architectures, including human-in-the-loop and autonomous frameworks. Define memory, context, planning … CrewAI, AutoGen, DSPy, Semantic Kernel, Strands. Advanced retrieval : Graph RAG, knowledge graphs, context graphs, hybrid search, vector databases. Agentic patterns : multi-agent architectures, planning and reasoning, MCP (Model Context Protocol). Model customization: fine-tuning, distillation, and model evaluation at scale. What ...

regulatory considerations into scalable, production-ready AI architectures. Design and implement advanced GenAI solutions, including: Retrieval-Augmented Generation (RAG) Multi-Agent Systems Knowledge Management Platforms Enterprise Workflow Automation Define architecture patterns, governance standards, security controls, and best practices for enterprise ...

output and productivity. Identify bottlenecks, repetitive work and opportunities where technology could fundamentally change how the work gets done. Multi-Agent Development: Design and deploy multi-agent systems where distinct AI personas collaborate … video/audio APIs, social publishing APIs, creative tools and platforms, and logistics trackers. Guardrails & Reliability: Design robust human checkpoints. Ensure the AI system fails gracefully, asks for human clarification when unsure, and, for example, never hallucinates brand guidelines or publishes without approval. Data & Infrastructure: Implement data retention ...

pair programming, code review, and design feedback. Raise the engineering bar across the team by promoting good practices in testing, observability, and AI system reliability. Influence cross-team decisions on how AI capabilities integrate with the rest of the Elliptic platform. What you will achieve in the first … workflow. Bonus points for: Experience with retrieval-augmented generation (RAG) and vector databases (pgvector, Pinecone, or similar). Experience designing multi-agent systems and agent orchestration patterns. Familiarity with LLM observability tools (LangSmith, Langfuse, Arize, or similar ...

Generative AI and Agentic AI architectures Architecting production-grade LLM applications and AI platforms Designing agentic workflows, orchestration and multi-agent systems Leading technical discovery and architecture discussions with enterprise clients Making key decisions around models, frameworks, infrastructure and deployment Remaining … Strong Python and modern AI/ML engineering knowledge Experience with major cloud platforms such as AWS, Azure or GCP Strong architecture and system-design capability Experience communicating complex technical concepts to senior stakeholders Previous technical leadership at Principal, Lead, Staff or Architect level Package ...

operations Building and integrating LLM, Generative AI and RAG solutions Developing AI assistants, copilots and agentic AI workflows Experimenting with multi-agent orchestration and knowledge retrieval Developing AI solutions using Python and modern AI frameworks Working with vector databases and retrieval technologies …/API development LLMs and Generative AI RAG implementation Prompt engineering and optimisation AI assistants/copilots Agentic AI or multi-agent systems Python development Vector databases and knowledge retrieval AI evaluation and model testing API integration and secure software engineering ...

databases, prompt engineering, and the latest API releases Someone who can go from "here's a new model" to "here's a production system" without hand-holding Experienced in building with OpenAI, Anthropic, Gemini, and open-source models Comfortable implementing everything from simple ChatGPT integrations to complex agentic … that lightly. What You Will DO Design and build production AI systems that solve real problems Implement RAG pipelines, multi-agent systems, and LLM-powered features Optimize for cost, latency, and accuracy across different AI services Create robust evaluation frameworks ...

Spark, or similar cloud-based data platforms. Ability to influence senior stakeholders and lead technical strategy Desirable Experience Experience building multi-agent AI systems and orchestration frameworks. Background within insurance, financial services, or other highly regulated environments. MSc, PhD, or equivalent ...

leading financial services clients. You’ll work hands‐on across the full AI engineering lifecycle, from architecting intelligent multi‐agent systems to deploying scalable production‐grade AI applications within enterprise environments. As a senior consultant, you’ll also collaborate closely with ...

Build the multi-agent systems that automate work banks currently do by hand. You'll own the orchestration, the auditability, and the evals that make our agents trustworthy. Mid–senior IC 3 days/week in office Visa sponsorship available Thanks ...

deployments, and provide technical leadership across the delivery lifecycle. Role requires hands-on expertise in AI engineering, LLMs, RAG, and multi-agent systems, with cloud experience across Azure, AWS, or GCP. Flexible/remote working and strong career progression are offered. ...

London. The successful candidate will have 6+ years of software engineering, strong Python skills, and hands-on experience with multi-agent AI systems and LLM #J-18808-Ljbffr ...

Applied Artificial Intelligence Engineers to join multiple positions. You will build and ship agentic AI systems in production, designing multi-agent pipelines and integrating large language models and vision-language models into real workflows for defence and national security customers. This ...

Senior Applied AI Engineer at Oxford Dynamics, you will build and ship agentic AI systems in production: designing the multi-agent pipelines, the reasoning and retrieval, the model integration, and the infrastructure that carries them into production. These are systems … system someone can stake a decision on. Key Responsibilities Build the systems themselves. You design and build multi-agent AI systems from the ground up, using frameworks such as LangGraph or Haystack where they help, and building ...

workloads, degraded connectivity, secure infrastructure and fully offline or air-gapped deployments. What You'll Be Doing Design and build multi-agent AI systems from the ground up, using frameworks such as LangGraph, LangChain, Haystack or similar where appropriate. Develop … generative AI or agentic systems. A strong track record operating at Senior, Lead or equivalent engineering level. Commercial experience building multi-agent or agentic AI systems for production , rather than simply integrating existing tools. Strong Python development skills and excellent software ...

deployment of secure, scalable, and reusable AI solutions using approved enterprise platforms and technologies. Build and integrate LLM, RAG, and multi-agent solutions using frameworks such as Semantic Kernel, LangChain, or similar. Develop and maintain AI-powered applications, APIs, and backend services. … experience developing AI-powered applications and services. Experience in backend development for AI applications and orchestration of LLMs or multi-agent systems. Experience with Azure OpenAI, Azure AI Foundry, AWS Bedrock, Vertex AI, or similar AI platforms. Experience in prompt engineering ...

high-value contracts, collaborating with our CTO to deliver production-grade AI for Fortune 500 procurement teams. You will design multi-agent systems, deploy LLM workflows, and connect AI agents to major procurement tools (SAP, Oracle, Coupa, GEP) while ensuring security ...

machine learning research. You'll be embedded in a cutting-edge team working on LLMs, RL, synthetic data, and multi-agent systems. This unusually research-heavy engineering role involves building robust infrastructure to support experiments and deploying production-quality code at scale. ...

orchestration frameworks, memory architectures, and tool-use capabilities. Developing custom AI workflows using large language models, retrieval systems, and multi-agent architectures. Collaborating closely with product and engineering teams to embed AI into real-world business processes. Contributing to the architecture … LangChain, Hugging Face, PyTorch, or similar technologies. Deep understanding of LLMs, RAG architectures, vector databases, prompt engineering, agentic AI, and multi-agent systems. Experience deploying, monitoring, and optimising AI solutions in production environments. A builder's mindset with a passion for solving ...

automated extracts connecting our MarTech - GA4, SEO/GEO data, and paid media platforms (LinkedIn, Google Ads, Meta) to the central data warehouse. System Integration & Webhooks: Design, implement, and monitor robust API integrations, webhooks, and middleware to sync real-time data across Marketo, Salesforce, Revenue Systems tools … feed enriched data back into revenue systems and the warehouse. Emerging Tech Exploration: Experiment with and pilot multi-agent orchestration systems, LLM-powered workflows, and protocols (such as MCP or multi-agent ...

Build the multi-agent reasoning systems that plan, hypothesize, and validate attack paths autonomously. Cyrion’s core product is a swarm of coordinated LLM-driven agents that reason about attack surfaces the way a human red teamer would. … memory across the swarm. Reduce false-positive rate by tightening the confidence-scoring and validation handoff logic. Ship incrementally — this is a production system with real customers, not a research sandbox. What we're looking for 3+ years building production ML or LLM-backed systems. Strong Python; comfortable ...