Ai Engineer Backend (Remote - Es/Uk Only)

pbAbout Us /b /ppQuadrivia is the health technology company behind Q, a comprehensive, controllable, and customizable assistant AI built by clinicians, for clinicians.Addressing the urgent shortage of healthcare professionals, Q provides real-time, personal, and reliable support for clinical tasks across the care continuum.Designed for providers, payers, and pharmaceutical companies, Q is easy to customise and integrates seamlessly into workflows, delivering precise assistance across the care spectrum./ppbr/ppbThe Role /b /ppYou'll build and run Cortex, the core AI architecture behind Qu, and the services that sit on top of it: automated AI audits, patient simulators, retrieval (RAG), and the escalation agents that take over in red-guardrail situations.This is a backend role first.The job is to make our AI systems reliable, fast, and observable in production, not to invent new ML.You own the software underneath the agents./ppWe're a small team that ships real systems.We've built our entire AI-driven evaluation system, our voice orchestrator, and a multi-hierarchical RAG platform from scratch./ppbr/ppbWhat You'll Do /b /pulliDesign and maintain robust, modular backend systems using clean architectural (SOLID) principles to ensure long-term maintainability, scalability and flexibility as the agentic stack evolves./liliOwn Cortex end-to-end: architecture, API design, service boundaries, reliability targets, and proactively managing failure modes./liliBuild the platform services around it.The automated audit and eval pipeline, patient simulators for testing agents at scale, and the retrieval layer./liliWrite fast, well-tested Python services with FastAPI, asyncio, and pydantic, and get the queues, caching, and data stores right./liliWire up the multi-agent orchestration: routing between agents, shared state, and clean tool interfaces./liliEngineer the RAG pipeline for high-signal retrieval (chunking, hybrid search, re-ranking, caching) and prove the grounding holds./liliMake the whole thing observable: structured logs, OTEL tracing across the agent graph, cost, latency and token visibility, dashboards, and CI gates that catch regressions before they ship./li /ulpbr/ppbMinimum Qualifications /b /pulliYour core is backend and software engineering.You write clean, maintainable services and you care how they behave in production./liliDeep understanding of architectural design patterns (e.g., Clean/Hexagonal Architecture, Domain-Driven Design, SOLID, event-driven) to manage complex system boundaries./liliAt least 2 years, demonstrable, building or scaling user-facing AI software that real users touched.We'll want to see it./liliExpert Python, with strong FastAPI, asyncio, pydantic, and production observability./liliComfortable with agent patterns and eval-driven development./liliYou've worked at a startup before and know what wearing several hats actually costs./li /ulpbr/ppbNice to Have /b /pulliReal-time and voice: WebRTC, LiveKit, SIP, VAD, barge-in, turn-taking.Useful here, not required./liliProgrammatic prompt optimization techniques./liliLLM-as-judge setups and other evaluation tooling./liliGCP: Cloud Run or GKE, Pub/Sub, Vertex AI, GCS, Secret Manager, Cloud Logging and Trace./liliHealthcare data familiarity./li /ulpbr/ppbExample Problems You'll Tackle /b /pulliStand up the AI audit pipeline so evals run automatically on slices of production traffic, with regression gates wired into CI./liliBuild a patient simulator that lets us stress-test agents at scale before they ever reach a real call./liliImprove the RAG pipeline with hybrid retrieval and re-ranking, then prove the gains with faithfulness and context metrics./liliGet OTEL-first tracing across the agent graph, with automated eval triggers on live traffic./liliTurn EHR integrations into reliable tools the agents can call./li /ulpbr/ppbTech Stack /b /ppPython, FastAPI, pydantic, asyncio, Redis, Postgres, vector stores, Docker, Kubernetes, Terraform, ArgoCD, OTEL, TypeScript, React.Real-time stacks (WebRTC, LiveKit, SIP, STT/TTS) where the work touches voice./ppbr/ppbWhat Success Looks Like /b /pulliQuadrivia's backend becomes a reference for reliability, safety, and performance./liliYour services run above *****% availability under strict regulatory constraints./liliOther engineers build new clinical workflows and agent capabilities quickly and safely./liliAI-generated code gets reviewed, corrected, and owned by you./li /ulpbr/p

You write clean, maintainable services and you care how they behave in production. /liliDeep understanding of architectural design patterns (e.g., Clean/Hexagonal Architecture, Domain-Driven Design, SOLID, event-driven) to manage complex system boundaries. /liliAt least 2 years, demonstrable, building or scaling user-facing AI software that real users touched.

Alicante, España pbAbout Us /b /ppQuadrivia is the health technology company behind Q, a comprehensive, controllable, and customizable assistant AI built by clinicians, for clinicians. Addressing the urgent shortage of healthcare professionals, Q provides real-time, personal, and reliable support for clinical tasks across the care continuum. Designed for providers, payers, and pharmaceutical companies, Q is easy to customise and integrates seamlessly into workflows, delivering precise assistance across the care spectrum. /ppbr/ppbThe Role /b /ppYou'll build and run Cortex, the core AI architecture behind Qu, and the services that sit on top of it: automated AI audits, patient simulators, retrieval (RAG), and the escalation agents that take over in red-guardrail situations. This is a backend role first. The job is to make our AI systems reliable, fast, and observable in production, not to invent new ML. You own the software underneath the agents. /ppWe're a small team that ships real systems. We've built our entire AI-driven evaluation system, our voice orchestrator, and a multi-hierarchical RAG platform from scratch. /ppbr/ppbWhat You'll Do /b /pulliDesign and maintain robust, modular backend systems using clean architectural (SOLID) principles to ensure long-term maintainability, scalability and flexibility as the agentic stack evolves. /liliOwn Cortex end-to-end: architecture, API design, service boundaries, reliability targets, and proactively managing failure modes. /liliBuild the platform services around it. The automated audit and eval pipeline, patient simulators for testing agents at scale, and the retrieval layer. /liliWrite fast, well-tested Python services with FastAPI, asyncio, and pydantic, and get the queues, caching, and data stores right. /liliWire up the multi-agent orchestration: routing between agents, shared state, and clean tool interfaces. /liliEngineer the RAG pipeline for high-signal retrieval (chunking, hybrid search, re-ranking, caching) and prove the grounding holds. /liliMake the whole thing observable: structured logs, OTEL tracing across the agent graph, cost, latency and token visibility, dashboards, and CI gates that catch regressions before they ship.