Wizeline, a integral AI-native technology solutions provider, develops cutting-edge, AI-powered digital products and platforms. We partner with clients to leverage data and AI, accelerating market entry and driving business transformation. As a global community of innovators, we foster a culture of growth, collaboration, and impact.

With the right people and the right ideas, there's no limit to what we can achieve.

Sounds awesome, right? Now, let's make sure you're a good fit for the role:

Key Responsibilities

Architect and ship end-to-end agentic and LLM-powered tools for business-facing use cases, deciding when to use a single LLM call, an iterative LLM loop, or a full multi-agent system based on real task complexity.

Design AI-agnostic, model-flexible services that allow the team to evaluate and swap the best-performing model for each task.

Build production tools that transform raw content into structured, ready-to-use output — for example, systems that reformat content to defined templates/guidelines or consolidate multiple sources into a single,



fact-accurate output without inventing information.

Develop and maintain RAG pipelines and vector database integrations to support retrieval-driven features such as content linking and recommendations.

Establish and scale prompt evaluation, testing, and regression-control frameworks (e.g., via Braintrust, MCP tooling, LangFuse) so quality holds as tools expand across teams and use cases.

Take AI features from prototype/PoC through to deployed, end-user-facing production tools, working across the full stack (AI core services in Python/TypeScript, front-end integration in React/Vue/Next.js) without relying on handoffs to other teams.

Partner with stakeholders and engineering leadership to gather feedback, measure impact (e.g., time saved, approval rates), and iterate on tools in production.

Extend proven architectures to onboard new use cases as configuration rather than one-off rebuilds.

Stay current on GenAI,

📌 AI Engineer (Madrid)
🏢 Wizeline
📍 Madrid