Prompt & AI/ML Engineer - Chatbot Voice Agent LLM & RAG

Job Title: Prompt & AI/ML Engineer – Chatbot LLM & RAGOverview At  QuantumLoopAI , we’re redefining customer engagement in healthcare with  EMMA , the UK’s leading AI receptionist for GP practices. By combining cutting-edge Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), advanced prompt engineering, and our bespoke voice agent technology, we eliminate phone queues, accelerate call handling and enhance patient access—transforming the primary care experience end-to-end. As our Senior Prompt & AI/ML Engineer, you will drive the design, development and deployment of the AI models that power EMMA’s intelligent chatbots, voice agent and telephony services. You’ll collaborate closely across product, engineering and clinical teams to deliver data-driven improvements, ensuring our solutions remain at the forefront of NHS digital transformation.Architect & Deploy AI Models: Lead the end-to-end development of LLM- and RAG-based systems to ingest NHS data sources, generate accurate responses, and power both chatbot and  voice agent interactions. Prompt & Voice Agent Engineering: Craft, iterate and optimise prompts—and design voice-agent dialogue flows—to maximise response relevance, reduce latency and ensure clinical safety across text and voice channels. Partner with frontend (Next.js, React) and backend (NestJS, Python) teams to integrate AI and voice agent components into our Azure-hosted microservices architecture. Performance Monitoring & Optimisation: Instrument AI and voice-agent pipelines, analyze logs and user feedback, troubleshoot edge cases, and implement continuous-learning improvements. Innovation & R&D: Stay abreast of the latest advances in LLMs, RAG, conversational AI frameworks, and NHS-specific compliance (GDPR, DTAC) to inform our technical roadmap. Testing & Validation: Define and execute rigorous test plans in collaboration with QA to validate model accuracy, voice-agent performance and compliance with healthcare standards. Technical Leadership: Mentor junior engineers, advocate for best practices in MLOps, prompt engineering, voice-agent design, and model governance, and contribute to architecture reviews. Hands-on experience with prompt engineering, LLMs (e.g., GPT, Bloom, LLaMA), RAG frameworks, and voice-agent/dialogue-system design, with demonstrable projects or open-source contributions. Programming Skills: Advanced proficiency in Python; comfortable building APIs in NestJS; familiarity with Next.js/React for frontend integration. Cloud & Data: Strong understanding of Azure services (App Services, Functions, Cognitive Services), containerisation (Docker), and relational databases (MySQL). Experience designing microservices, distributed architectures and RESTful/GraphQL APIs. Excellent written and verbal skills to articulate complex AI and voice-agent concepts to technical and non-technical stakeholders. Impactful Work: Shape the AI and  voice agent engine behind  EMMA , directly improving patient access and staff wellbeing across hundreds of GP surgeries. Innovative Environment: Join a rapidly growing team at the cutting edge of healthcare AI, with dedicated R&D time and full support for professional development. Flexible Hybrid Working: Our HQ at Canary Wharf is just a short walk from the DLR; enjoy a balance of in-office collaboration and remote days. Attractive salary, equity options, pension contributions and comprehensive private healthcare. Work alongside seasoned AI researchers, software engineers and NHS specialists in a collaborative, fast-paced setting. QuantumLoopAI is the UK’s market-leading provider of AI-powered telephony,  voice agent and chatbot solutions for primary care. Our flagship product,  EMMA , streamlines patient communications, slashes call-handling costs by up to 80%, and aligns seamlessly with NHS systems and regulations. Join us in our mission to transform healthcare access through intelligent automation. Ready to transform patient care with AI?