The English-language job board for Spain

AI Engineer

Remote, València·Full-time·Added 5 days ago

Laberit

14 open roles

Overview

Job details

  • Full-time hours

    Per the ad.

  • Fully remote

    Only from certain places, per the ad: “Residir en Valencia o Madrid”

Requirements

  • Have the right to work in Spain

    Laberit doesn't mention sponsorship in the ad.

  • Speak fluent Spanish

    Listed as a requirement in the ad.

  • Work in English

    English is required, per the ad.

  • Have 3+ years of experience

    Mid-level role.

This job was automatically translated to English.

Requirements

What we're looking for

  • 3+ years developing production software, with at least 1 year taking LLM-based systems beyond the demo: not chat wrappers, but systems with tools, state, and real failures.
  • Demonstrable experience designing tool interfaces for agents: typed schemas, input validation, idempotency, and errors that the model can use to correct itself.
  • Deep understanding of context management: what goes into the window and why, compaction, external memory in the filesystem, cache-aware ordering.
  • Knowledge of MCP at an implementation level, not a user level: having written a server, understanding tools/resources/prompts, transports, and authorization.
  • An evaluation-first rather than intuition-first mindset: experience defining metrics and evaluation datasets for non-deterministic systems with LangSmith, Braintrust, Langfuse, Ragas, DeepEval, OpenAI Evals, or similar. If you don't know how to measure if a change improved something, it isn't a change.
  • Proficiency in Python and TypeScript, and the ability to critically read code you haven't written—whether your own or generated—to review and reject it.
  • Experience designing relational schemas and authentication and authorization flows (e.g., Supabase).
  • Security judgment in agentic systems: indirect injection surface, least privilege, execution isolation, sensitive data handling.
  • Solid knowledge of Docker and CI pipelines.
  • Fluent level of Spanish and English (oral and written).
  • Reside in Valencia or Madrid

Excellent communication and a high sense of responsibility and autonomy.

Nice to have

It will be a plus if:

  • Experience with applied fine-tuning (LoRA/QLoRA, SFT, distillation) and, above all, evidence of having evaluated whether it was worth it compared to adjusting the harness.
  • Experience serving your own inference: vLLM, SGLang, TensorRT-LLM, or similar; continuous batching, quantization, GPU sizing, and cost per token versus API.
  • Experience with ASR and voice models applied to the clinical domain.
  • Knowledge of real-time communications (WebSockets, WebRTC) and streaming APIs.
  • Public contributions: MCP servers, skills, agent tools, papers, or benchmarks.
  • Knowledge of the healthcare sector and regulations such as GDPR, MDR, or HIPAA.

The role

We are looking for a Senior Full-Stack Engineer dedicated to the development of our MarIA platform: a web application that allows healthcare professionals to configure, monitor, and manage our real-time voice-to-voice AI agent.

You will work with our core team, ensuring that the application scales seamlessly to tens of thousands of simultaneous AI conversations.

Functions:

What you'll do

  • Design and maintain our clinical agents' harness: agentic loop, tool registry, token budget management, stop conditions, context compaction, and retry policy.
  • Define the appropriate multi-agent topology for each problem (sub-agents with isolated context, skills, handoffs, router) and justify why that one and not another.
  • Build long-horizon planning loops with state persisted in the filesystem: plan files, resumption checkpoints, and human-in-the-loop control points before irreversible actions on patient data.
  • Package clinical procedural knowledge as Skills (SKILL.md, progressive disclosure) and external capabilities as proprietary MCP servers over HIS/EHR, with permissions by risk level (read / write / destructive).
  • Set up and grow our agent evaluation layer: regression datasets, LLM-as-a-judge with auditable criteria, automatic evals that block changes to the harness, and security evals of the harness itself (indirect injection via clinical content, timeouts, tool overuse), using LangSmith, Braintrust, Langfuse, promptfoo, DeepEval, Inspect, or similar.
  • Securely integrate our systems with hospitals and Electronic Health Record (EHR) platforms, including the permission model and traceability of what the agent reads and writes.
  • Instrument agents with span-based traces (Langsmith, OpenTelemetry, Sentry, or similar): cost, latency per tool, success rate per step, transcription quality, and prompt cache hit rate.
  • Develop and evolve the web application through which healthcare professionals interact with our agents, with the judgment to direct and review generated code.
  • Improve backend infrastructure and automate deployments with Docker and GitHub Actions, taking care of the developer experience and the isolated environments where the agents run.
  • Participate in key architectural decisions: what is solved with a model, what with a deterministic harness, and what with plain code.

About Laberit

Laberit delivers IT services for companies and public administrations, including custom application development, business intelligence (Microsoft Power BI, Qlik), ERP implementation (Microsoft Dynamics 365 Business Central, Odoo), cybersecurity, cloud, AI, RPA, supply chain and Industry 4.0 solutions, and its SINA hospital management system (HIS). It reports having taken part in more than 10,000 projects across sectors such as public administration, healthcare, industry, banking, telecommunications and energy.

For international professionals, LÃBERIT offers roles across multiple Spanish cities — Valencia, Madrid, Murcia, Las Palmas de Gran Canaria and Santa Cruz de Tenerife — as well as positions in Buenos Aires, Ciudad de México, Rome and Santiago, several of them fully remote. Its healthcare division hires HIS implementation consultants with French and Arabic, pointing to international eHealth projects. The company describes its culture as close, collaborative and flexible, with continuous learning and knowledge sharing, and it runs internship programs for students in fields such as computer engineering and biomedicine.

Industry
IT Services
Employees
1,100+
In Spain
Valencia

Good to know if you are moving

  • Hiring across several Spanish cities: Valencia, Madrid, Murcia, Las Palmas de Gran Canaria and Santa Cruz de Tenerife, plus international locations in Buenos Aires, Ciudad de México, Rome and Santiago.
  • Several open roles are fully remote (Teletrabajo/Remoto) or hybrid, including positions based outside Spain.
  • Its healthcare (eSalud) division recruits HIS implementation consultants with French and Arabic language skills, indicating international hospital IT projects.
  • Runs internship programs ('Prácticas') for students in computer engineering and biomedicine, mainly in Valencia and Las Palmas de Gran Canaria.
All open roles at Laberit
WhatsApp