Descripción de la oferta
About the Role We are looking for a hands‑on AI Engine to owner and evolve the core “brain” service that drives a cutting‑edge AI product. This role spans architecture, development, optimization, and production operations of real‑time, multi‑agent LLM systems. Role Overview As an AI Engineer, you will design, build, and operate low‑latency, real‑time text and voice agent systems. You will be responsible for multi‑agent orchestration, advanced reasoning approaches, RAG engineering, and evaluation‑driven development to ensure production‑grade quality and performance. Key Responsibilities Design, build, and operate low‑latency real‑time text and voice agent systems Implement multi‑agent orchestration patterns (planner–executor–critic, routing, shared memory) Apply advanced reasoning methods (ReAct, Chain‑of‑Thought, Tree‑/Graph‑of‑Thoughts where appropriate) Lead RAG engineering with strong grounding, evaluation, and observability Drive evaluation‑based development with monitoring, tracing, and CI/CD gating Ship production‑grade Python services using FastAPI under strict latency and quality requirements Minimum Qualifications 5+ years of experience in ML or backend engineering in production environments Deep expertise in Python, FastAPI, asyncio, and production observability Experience with low‑latency text and/or voice systems (LiveKit, Pipecat, WebRTC, or similar) Hands‑on experience with LLM systems, agent patterns, and evaluation‑driven workflows Prior startup experience What We Offer Work on state‑of‑the‑art real‑time AI agent technology in healthtech Highly collaborative, senior technical team Fully remote role based in Barcelona Fun off‑sites and strong developer ergonomics If you are interested please email your CV to for immediate consideration. #J-18808-Ljbffr
