Job Description
We are looking for an innovative AI / LLM Engineer to drive the advancement of our conversational AI capabilities. You'll join our Tech&Product team as an AI / LLM Engineer , 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.
What will you do?
Core Development
- Design, optimize, and version prompts for production voice and chat LLM applications
- Architect and orchestrate multi-agent systems for complex conversations
- Build automated testing and validation frameworks for LLM outputs
- Implement prompt versioning, storage, and retrieval systems
System Integration & Deployment
Collaborate with Backend Engineers to deploy and scale LLM-based systemsIntegrate LLMs with communication APIs (Twilio, WhatsApp, ElevenLabs)Implement RAG (Retrieval-Augmented Generation) solutions and vector search for multilingual environmentsMonitor performance metrics and conversation qualityResearch & Innovation
Research and prototype multi-agent frameworks (open-source and commercial)Experiment with cutting-edge conversational AI and real-time speech processing techniquesContribute to evolving the team's LLMOps best practicesContinuously improve conversational quality, RAG pipelines, and reduce latencyQualifications
Must have
2+ years hands-on experience with LLMs (OpenAI or similar, open-source models)Strong knowledge in prompt engineering and LLM optimization strategiesExperience in evaluating LLMs, designing and running evaluation frameworks, creating test datasets, and defining success metricsFamiliarity with automated testing pipelines, building CI / CD-integrated eval systems that run on every prompt changeExperience in multi-agent architecture, from design to development of orchestration of complex LLM systemsGood understanding of transformer architectures and proficiency in LLM frameworks such as LangChain, LlamaIndex, or similar frameworksProficiency in PythonExperience with RAG pipelines and vector databasesExperience 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.Nice to have
Experience in healthcare industriesLLM integration with voice platforms (Twilio, ElevenLabs)Background in conversational AI, chatbots, voice assistantsKnowledge of real-time speech processing and multi-modal systemsFunctional programming principles and advanced NLPExposure to OOP stacks (.NET, PHP)Understanding of security and privacy in conversational AIAdditional Information
✨ What we offer :
We value a healthy work-life balance and long-term growth. Benefits vary by location, but here’s what you can expect :
Shared benefits
100% remote work, with the option to join our offices in Bologna or BarcelonaStock options plan after 6 monthsOne extra day off for your birthdayAccess to iFeel – our mental wellbeing platformItaly-specific
️ €8 / day meal vouchers – lunch is covered if you're in the Bologna officePrivate health coverage via MetasaluteSpain-specific
❤️ Comprehensive private health insurance with AdeslasFlexoh – flexible compensation platformWellhub – gym & wellness network membershipLanguage coursesHow does the recruitment process work?
HR interview – a friendly chat to get to know you, your motivations, and tell you more about Tuotempo, our culture, and the team.Technical 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.Functional interview — a conversation with our Product Managers to understand how you collaborate cross-functionally and to align on the AI product domain.