ph3About Us /h3 pQuadrivia 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 customize and integrates seamlessly into workflows, delivering precise assistance across the care spectrum. /p h3The Role /h3 pYou’ll build and run Cortex, the core AI architecture behind Q, 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. /p h3What You’ll Do /h3 ul liDesign and maintain robust, modular backend systems using clean architectural (SOLID) principles to ensure long‑term maintainability, scalability and flexibility as the agentic stack evolves. /li liOwn Cortex end‑to‑end: architecture, API design, service boundaries, reliability targets, and proactively managing failure modes. /li liBuild the platform services around it: the automated audit and eval pipeline, patient simulators for testing agents at scale, and the retrieval layer. /li liWrite fast, well‑tested Python services with FastAPI, asyncio, and pydantic, and get the queues, caching, and data stores right. /li liWire up the multi‑agent orchestration:



routing between agents, shared state, and clean tool interfaces. /li liEngineer the RAG pipeline for high‑signal retrieval (chunking, hybrid search, re‑ranking, caching) and prove the grounding holds. /li liMake 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 /ul h3Minimum Qualifications /h3 ul liYour core is backend and software engineering. You write clean, maintainable services and you care how they behave in production. /li liDeep understanding of architectural design patterns (e.g., Clean/Hexagonal Architecture, Domain‑Driven Design, SOLID, event‑driven) to manage complex system boundaries. /li liAt least 2 years, demonstrable, building or scaling user‑facing AI software that real users touched. We’ll want to see it. /li liExpert Python, with strong FastAPI, asyncio, pydantic, and production observability. /li liComfortable with agent patterns and eval‑driven development. /li liYou’ve worked at a startup before and know what wearing several hats actually costs. /li /ul h3Nice to Have /h3 ul liReal‑time and voice: WebRTC, LiveKit, SIP, VAD, barge‑in,



turn‑taking. Useful here, not required. /li liProgrammatic prompt optimization techniques. /li liLLM‑as‑judge setups and other evaluation tooling. /li liGCP: Cloud Run or GKE, Pub/Sub, Vertex AI, GCS, Secret Manager, Cloud Logging and Trace. /li liHealthcare data familiarity. /li /ul h3Example Problems You’ll Tackle /h3 ul liStand up the AI audit pipeline so evals run automatically on slices of production traffic, with regression gates wired into CI. /li liBuild a patient simulator that lets us stress‑test agents at scale before they ever reach a real call. /li liImprove the RAG pipeline with hybrid retrieval and re‑ranking, then prove the gains with faithfulness and context metrics. /li liGet OTEL‑first tracing across the agent graph, with automated eval triggers on live traffic. /li liTurn EHR integrations into reliable tools the agents can call. /li /ul h3Tech Stack /h3 pPython, 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. /p h3What Success Looks Like /h3 ul liQuadrivia’s backend becomes a reference for reliability, safety, and performance. /li liYour services run above 99.99% availability under strict regulatory constraints. /li liOther engineers build new clinical workflows and agent capabilities quickly and safely. /li liAI‑generated code gets reviewed, corrected, and owned by you. /li /ul /p #J-18808-Ljbffr

📌 AI Engineer Backend (Remote - ES/UK only) (Barcelona)
🏢 Quadrivia AI
📍 Barcelona