Ph3Company Description /h3 pWe transform healthcare experiences through intelligent digital solutions. /p pTuotempo is the trusted patient engagement platform powering some of Europe and Latin America's leading healthcare institutions. Our innovative CRM system liberates medical professionals from administrative burdens so they can focus on their true passion: delivering exceptional patient care. /p pOur cloud-based platform seamlessly orchestrates the entire patient journey—from initial appointment booking through omnichannel appointment management and extending to comprehensive follow‑up care. The result? Streamlined operations for providers and a frictionless experience for patients. /p pDiscover how we're reshaping healthcare delivery at tuotempo.com /p pEmbrace flexibility with our remote‑first culture: Work entirely remotely from Italy or Spain, or collaborate in‑person at our vibrant hubs in Bologna or Barcelona—we believe in empowering you to work where you thrive! /p h3Job Description /h3 pWe are looking for an innovative bAI/LLM Engineer /b to drive the advancement of our conversational AI capabilities. You'll join our TechProduct team as an bAI/LLM Engineer /b, focusing on prompt engineering, multi‑agent orchestration, automated testing, and deploying integrations in production with LLM systems. You'll work closely with Backend Engineers to deliver world‑class AI experiences to end users. /p h3What will you do? /h3 h3Core Development /h3 ul liDesign, optimize, and version prompts for production voice and chat LLM applications /li liArchitect and orchestrate multi‑agent systems for complex conversations /li liBuild automated testing and validation frameworks for LLM outputs /li liImplement prompt versioning, storage, and retrieval systems /li /ul h3System Integration Deployment /h3 ul liCollaborate with Backend Engineers to deploy and scale LLM‑based systems /li liIntegrate LLMs with communication APIs (Twilio, WhatsApp, ElevenLabs) /li liImplement RAG (Retrieval‑Augmented Generation) solutions and vector search for multilingual environments /li liMonitor performance metrics and conversation quality /li /ul h3Research Innovation /h3 ul liResearch and prototype multi‑agent frameworks (open‑source and commercial) /li liExperiment with cutting‑edge conversational AI and real‑time speech processing techniques /li liContribute to evolving the team's LLMOps best practices /li liContinuously improve conversational quality, RAG pipelines, and reduce latency /li /ul h3Qualifications /h3 h3Must have /h3 ul li2+ years hands‑on experience with LLMs (OpenAI or similar, open‑source models) /li liStrong knowledge in prompt engineering and LLM optimization strategies /li liExperience in evaluating LLMs, designing and running evaluation frameworks, creating test datasets, and defining success metrics /li liFamiliarity with automated testing pipelines, building CI/CD‑integrated eval systems that run on every prompt change /li liExperience in multi‑agent architecture, from design to development of orchestration of complex LLM systems /li liGood understanding of transformer architectures and proficiency in LLM frameworks such as LangChain, LlamaIndex, or similar frameworks /li liProficiency in Python /li liExperience with RAG pipelines and vector databases /li liExperience in cross‑functional teams, ability to work in fast‑moving environments where you own outcomes, not just tasks. You're comfortable with ambiguity and excited by the challenge of figuring things out. /li /ul h3Nice to have /h3 ul liExperience in healthcare industries /li liLLM integration with voice platforms (Twilio, ElevenLabs) /li liBackground in conversational AI, chatbots, voice assistants /li liKnowledge of real‑time speech processing and multi‑modal systems /li liFunctional programming principles and advanced NLP /li liExposure to OOP stacks (.NET, PHP) /li liUnderstanding of security and privacy in conversational AI /li /ul h3Additional Information /h3 h3✨ What we offer: /h3 pWe value a healthy work‑life balance and long‑term growth. Benefits vary by location, but here’s what you can expect: /p h3Shared benefits /h3 ul li100% remote work, with the option to join our offices in Bologna or Barcelona /li liStock options plan after 6 months /li liOne extra day off for your birthday /li liAccess to iFeel – our mental wellbeing platform /li /ul h3Italy-specific /h3 ul li️ €8/day meal vouchers – lunch is covered if you're in the Bologna office /li liPrivate health coverage via Metasalute /li /ul h3Spain-specific /h3 ul li❤️ Comprehensive private health insurance with Adeslas /li liFlexoh – flexible compensation platform /li liWellhub – gym wellness network membership /li liLanguage courses /li /ul h3How does the recruitment process work? /h3 ul liHR interview – a friendly chat to get to know you, your motivations, and tell you more about Tuotempo, our culture, and the team. /li liTechnical interview – a deep‑dive with our Tech Managers, including practical discussions or small exercises focused on LLMs, multi‑agent systems, prompt design, and evaluation workflows. /li liFunctional interview —a conversation with our Product Managers to understand how you collaborate cross‑functionally and to align on the AI product domain. /li /ul /p #J-18808-Ljbffr