Sabio

CX solutions via cloud and consulting

AI Engineer

AI Application EngineeringUpdated on Nov 13

Full-timeMadrid, SpainNo salary listed

About the Job

Requirements

Hands-on experience delivering conversational AI, including voicebots, chatbots or virtual assistants, conversational flows, open-ended interactions, natural language understanding and generative AI.
Production experience building generative AI agents using agentic architectures, retrieval-augmented generation and orchestration.
Working knowledge of frontier large language model providers and platforms, including Anthropic Claude, OpenAI, Google Gemini, Amazon Bedrock and Microsoft Azure AI, and practical judgment about which to use.
Strong prompt engineering and context engineering skills across multiple large language model families, including system prompt design, structured output and grounding strategies.
Ability to measure agent quality using evaluation sets, traces and metrics.
Awareness of AI ethics, bias and safety, with practical experience mitigating these in deployed systems.
Ability to optimise token use, latency and cost through model routing, caching, context compression and retrieval tuning.
Comfort using AI coding assistants and AI co-work or pair-development models, such as Claude Code, Copilot or Cursor, in day-to-day delivery.
Solid software engineering fundamentals, including Python and/or JavaScript/Node, Git, IDEs and Agile delivery.
Customer-facing skills in requirements gathering, design, validation and stakeholder communication.
Working proficiency in Spanish and English.

Responsibilities

Translate customer experience and business needs into AI solution designs spanning natural language understanding and large language models, retrieval-augmented generation, automatic speech recognition and text-to-speech, and back-end integrations.
Define functional and non-functional requirements for latency, resiliency, observability, security and cost per conversation.
Design and build agentic AI solutions using single-agent, multi-agent, tool-using and orchestrated patterns with modern frameworks and frontier models.
Build and optimise natural language understanding and large language model components for classification, named entity recognition, summarisation and retrieval-augmented generation over enterprise knowledge bases.
Engineer prompts, tool schemas, context windows and token budgets for accuracy, latency and cost.
Develop data and knowledge pipelines for ingestion, cleansing, personally identifiable information redaction and evaluation datasets.
Build evaluation harnesses, including offline evaluation sets, large-language-model-as-judge, regression suites and A/B testing.
Drive continuous improvement through conversation analytics, error triage and failure-mode analysis.
Implement continuous integration and continuous delivery for models and prompts, with feature flags, canary releases and rollback.
Track experiments, lineage, and model and prompt versions.
Operate production services against service-level objectives with monitoring, tracing, alerting and incident response.
Apply practical guardrails for safety, bias, hallucination, prompt injection and jailbreak resistance.
Enforce GDPR and LOPDGDD requirements for consent, minimisation, retention, access control and auditability.
Work alongside conversation designers, software engineers, data scientists, quality assurance and operations.
Produce clear design documents, runbooks and stakeholder updates.

Desired Qualifications

Experience with cloud services, primarily AWS, and containerised deployment via Docker or Kubernetes.
Experience with contact centre integrations such as Genesys, Avaya, Cisco or Amazon Connect, and Meta, WhatsApp Business or digital-channel integrations.
Experience with automatic speech recognition and text-to-speech, and voice-specific concerns such as barge-in, turn-taking, speech recognition error recovery and latency budgets.
Experience with speech or natural language understanding recognition models and continuous-improvement loops, including Microsoft STT, Microsoft CLU, Google or Amazon offerings.
Experience with observability for large language model systems, including tracing, evaluation pipelines and online quality monitoring.
Familiarity with emerging agent interoperability standards such as MCP and A2A, and human-in-the-loop or escalation patterns.
Exposure to Microsoft Bot Framework, Genesys Dialog Engine or VXML.
Consulting experience analysing existing bot estates, evaluating key performance indicators such as containment, customer satisfaction, average handling time and transfer rate, and recommending improvements.
Exposure to Google Conversational Agent, Playbooks or Dialogflow.

At 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.

We're hiring an AI Engineer 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.

This 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.

Discovery & Design

Translate CX and business needs into AI solution designs spanning NLU/LLM, RAG, ASR/TTS and back-end integrations.
Define functional and non-functional requirements: latency, resiliency, observability, security, cost-per-conversation.

Agent & Model Implementation

Design and build agentic AI solutions — single-agent, multi-agent, tool-using and orchestrated patterns — using modern frameworks and frontier models.
Build and optimise NLU/LLM components: classification, NER, summarisation, RAG over enterprise knowledge bases.
Engineer prompts, tool schemas, context windows and token budgets for accuracy, latency and cost.
Develop data and knowledge pipelines for ingestion, cleansing, PII redaction and evaluation datasets.

Evaluation & Quality

Build evaluation harnesses (offline eval sets, LLM-as-judge, regression suites, A/B testing) and treat eval as a first-class deliverable, not an afterthought.
Drive continuous improvement via conversation analytics, error triage and failure-mode analysis.

LLMOps & Operations

Implement CI/CD for models and prompts, with feature flags, canary releases and rollback.
Track experiments, lineage, and model/prompt versions.
Operate services in production against SLOs with monitoring, tracing, alerting and incident response.

Responsible AI

Apply practical guardrails for safety, bias, hallucination, prompt-injection and jailbreak resistance.
Enforce GDPR / LOPDGDD: consent, minimisation, retention, access control, auditability.

Collaboration

Work alongside conversation designers, software engineers, data scientists, QA and Ops.
Produce clear design docs, runbooks and stakeholder updates.

Required

Hands-on experience delivering conversational AI — voicebots, chatbots or virtual assistants — including conversational flows, open-ended interactions, NLU and generative AI.
Production experience building agents with generative AI: agentic architectures (single-agent, multi-agent, tool/function-calling, planner–executor patterns), RAG, and orchestration.
Working 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.
Strong prompt engineering and context engineering skills across multiple LLM families, including system prompt design, structured output, and grounding strategies.
An evaluation mindset: you measure agent quality with eval sets, traces and metrics — not vibes.
Awareness of AI ethics, bias and safety, with practical experience mitigating them in deployed systems.
Token, latency and cost optimisation — model routing, caching (incl. prompt caching), context compression, retrieval tuning — as a core engineering discipline.
Comfort with agentic development workflows — 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.
Solid software engineering fundamentals: Python and/or JavaScript/Node, Git, IDEs, Agile delivery.
Customer-facing skills: requirements gathering, design, validation and stakeholder communication.
Working proficiency in Spanish and English.

Desirable

Cloud services, primarily AWS, with containerised deployment via Docker / Kubernetes.
Contact centre integrations (e.g. Genesys, Avaya, Cisco, Amazon Connect) and Meta / WhatsApp Business / digital channel integrations.
Experience with ASR/TTS and voice-specific concerns: barge-in, turn-taking, ASR error recovery, latency budgets.
Speech/NLU recognition models and continuous-improvement loops (Microsoft STT, MS CLU, Google, Amazon).
Observability for LLM systems: tracing, eval pipelines, online quality monitoring.
Familiarity with emerging agent interoperability standards (e.g. MCP, A2A) and human-in-the-loop / escalation patterns.
Microsoft Bot Framework, Genesys Dialog Engine or VXML exposure.
Consulting experience analysing existing bot estates, evaluating KPIs (containment, CSAT, AHT, transfer rate) and recommending improvements.

Nice to Have

Exposure to Google Conversational Agent / Playbooks or DialogFlow — useful if you've worked with it, but not required.

Sabio

AI Engineer

About the Job

Requirements

Responsibilities

Desired Qualifications

About the Company

Sabio

Recently Posted Jobs