Technical Lead

ABOUT QUANTUMLOOPAI

QuantumLoopAI is one of the UK's fastest-growing healthtech companies. Our AI-powered platform, EMMA, is used by hundreds of organisations across the UK to manage communications, automate workflows and deliver better outcomes through intelligent automation. Backed by leading investors and scaling rapidly ahead of our Series A, we are building the infrastructure that will define the next generation of AI-driven service delivery.

ABOUT THE ROLE

We are looking for a Technical Lead with 8+ years of experience in full-stack engineering (backend heavy) to lead architecture, development and technical strategy across our distributed systems and AI initiatives. You will work directly with the Co-Founder, translating product vision into technical execution, guiding a distributed engineering team, and driving the integration of cutting-edge AI capabilities — including LLM orchestration, voice agents, speech-to-text and text-to-speech pipelines — into a production platform that is scaling fast.

This role requires someone who can operate at the intersection of engineering leadership and hands-on delivery. You will set the technical direction, define architecture, and actively build — while mentoring engineers, shaping culture and challenging decisions at the highest level.

WHAT YOU WILL DO

• Technical Leadership and Architecture
• Lead design and implementation of scalable backend systems using Node.js, TypeScript and microservice architectures.
• Define and enforce coding standards, design principles and architecture guidelines across the engineering team.
• Ensure platform scalability, reliability and security through robust design and proactive system monitoring.
• Architect end-to-end AI-powered features from prototype to production, balancing speed with engineering rigour.

AI/ML and Prompt Engineering

• Design, build and maintain AI/ML-powered systems including chatbots, voice agents, RAG pipelines and multi-agent architectures.
• Own prompt engineering practices across the platform — crafting, testing, versioning and optimising prompts for LLMs (OpenAI, Azure OpenAI and open-source models).
• Implement evaluation frameworks to measure LLM output quality, hallucination rates, latency and cost.
• Integrate AI models into production environments and manage model lifecycle, versioning and observability.
• Leverage Azure Machine Learning, OpenAI APIs and multi-agentic frameworks (LangChain, AutoGen, CrewAI) to build intelligent, data-driven experiences.
• Champion the use of modern AI development tooling (Cursor, GitHub Copilot, Claude) across the engineering team.