ph3AI Engineer /h3pstrongDepartment: /strongDelivery /ppstrongEmployment Type: /strongFull Time /ppstrongLocation: /strongMadrid /pbrh3Description /h3pAt Sabio Group, we're building the next generation of AI-powered customer experience for some of the world's most demanding enterprise brands — the kind of frontier customers who set the bar for what "great CX" looks like. We pair frontier-class large language models with deep contact centre expertise to deliver agentic experiences that materially improve containment, CSAT and operational efficiency.br/ppWe're hiring an strongAI Engineer /strong to join our customer service bot / AI agent team in Madrid. You'll work end-to-end across the lifecycle — discovery, design, build, evaluate, deploy, operate — engineering robust LLM/NLU solutions, knowledge pipelines and integrations across voice and digital channels, primarily in Spanish.br/ppThis is a hands-on engineering role for someone who is curious about where AI is going, comfortable shipping agentic systems into production, and thoughtful about doing so safely and cost-effectively. /pbrh3Key Responsibilities /h3pstrongDiscovery Design /strong /pulliTranslate CX and business needs into AI solution designs spanning NLU/LLM, RAG, ASR/TTS and back-end integrations. /liliDefine functional and non-functional requirements: latency, resiliency, observability, security, cost-per-conversation. /li /ulpstrongAgent Model Implementation /strong /pulliDesign and build agentic AI solutions — single-agent, multi-agent, tool-using and orchestrated patterns — using modern frameworks and frontier models. /liliBuild and optimise NLU/LLM components: classification, NER, summarisation, RAG over enterprise knowledge bases. /liliEngineer prompts, tool schemas, context windows and token budgets for accuracy, latency and cost. /liliDevelop data and knowledge pipelines for ingestion, cleansing, PII redaction and evaluation datasets. /li /ulpstrongEvaluation Quality /strong /pulliBuild evaluation harnesses (offline eval sets, LLM-as-judge, regression suites, A/B testing) and treat eval as a first-class deliverable, not an afterthought. /liliDrive continuous improvement via conversation analytics, error triage and failure-mode analysis. /li /ulpstrongLLMOps Operations /strong /pulliImplement CI/CD for models and prompts,



with feature flags, canary releases and rollback. /liliTrack experiments, lineage, and model/prompt versions. /liliOperate services in production against SLOs with monitoring, tracing, alerting and incident response. /li /ulpstrongResponsible AI /strong /pulliApply practical guardrails for safety, bias, hallucination, prompt-injection and jailbreak resistance. /liliEnforce GDPR / LOPDGDD: consent, minimisation, retention, access control, auditability. /li /ulpstrongCollaboration /strong /pulliWork alongside conversation designers, software engineers, data scientists, QA and Ops. /liliProduce clear design docs, runbooks and stakeholder updates. /li /ulbrh3Skills Knowledge and Expertise /h3pstrongRequired /strong /pulliHands-on experience delivering conversational AI — voicebots, chatbots or virtual assistants — including conversational flows, open-ended interactions, NLU and generative AI. /liliProduction experience building agents with generative AI: agentic architectures (single-agent, multi-agent, tool/function-calling, planner–executor patterns), RAG, and orchestration. /liliWorking knowledge of frontier LLM providers and platforms — e.g. Anthropic Claude, OpenAI, Google Gemini, Amazon Bedrock, Microsoft Azure AI — and a practical sense of when to use which. /liliStrong prompt engineering and strongcontext engineering /strong skills across multiple LLM families, including system prompt design, structured output, and grounding strategies. /liliAn evaluation mindset: you measure agent quality with eval sets, traces and metrics — not vibes. /liliAwareness of AI ethics, bias and safety, with practical experience mitigating them in deployed systems. /lilistrongToken, latency and cost optimisation /strong — model routing, caching (incl. prompt caching), context compression, retrieval tuning — as a core engineering discipline.



/liliComfort with strongagentic development workflows /strong — using AI coding assistants and AI co-work / pair-development models (Claude Code, Copilot, Cursor or equivalent) as part of your day-to-day delivery. /liliSolid software engineering fundamentals: Python and/or JavaScript/Node, Git, IDEs, Agile delivery. /liliCustomer-facing skills: requirements gathering, design, validation and stakeholder communication. /liliWorking proficiency in Spanish and English. /li /ulpstrongDesirable /strong /pulliCloud services, primarily AWS, with containerised deployment via Docker / Kubernetes. /liliContact centre integrations (e.g. Genesys, Avaya, Cisco, Amazon Connect) and Meta / WhatsApp Business / digital channel integrations. /liliExperience with ASR/TTS and voice-specific concerns: barge-in, turn-taking, ASR error recovery, latency budgets. /liliSpeech/NLU recognition models and continuous-improvement loops (Microsoft STT, MS CLU, Google, Amazon). /liliObservability for LLM systems: tracing, eval pipelines, online quality monitoring. /liliFamiliarity with emerging agent interoperability standards (e.g. MCP, A2A) and human-in-the-loop / escalation patterns. /liliMicrosoft Bot Framework, Genesys Dialog Engine or VXML exposure. /liliConsulting experience analysing existing bot estates, evaluating KPIs (containment, CSAT, AHT, transfer rate) and recommending improvements. /li /ulpstrongNice to Have /strong /pulliExposure to Google Conversational Agent / Playbooks or DialogFlow — useful if you've worked with it, but not required. /li /ulbrh3Benefits /h3pThis is your chance to join and friendly and passionate team that will motivate you to learn and develop your career in the company.brstrongBenefits may include:br/strongbrPension SchemebrRemote/Adaptable workbrLife insurancebrHealth insurancebr25 days paid holiday a yearbrLinkedIn LearningbrPlus many more! (Benefits are dependant on your base location.)brstrongThe Small Print /strongbrStrictly No Agencies; any submission of resumes without prior request from Sabio Group will not be deemed as an introduction and therefore will not warrant an introduction fee. All applicants must have the right to work in the territory to which the role relates (UK EU). Sabio Group are unable to offer sponsorship on any roles advertised. /p /p #J-18808-Ljbffr

📌 AI Engineer - CX Bot & LLM Specialist (Madrid)
🏢 Sabio Group
📍 Madrid