Responsibilities
- Architect and ship end-to-end agentic and LLM-powered tools for business-facing use cases.
- Design model-versátil services that evaluate and switch between models based on performance.
- Build production systems that transform raw content into structured, accurate, ready-to-use outputs.
- Develop and maintain RAG pipelines and vector database integrations for retrieval-driven features.
- Establish prompt evaluation, testing, and regression-control frameworks using tools such as Braintrust, MCP tooling, or LangFuse.
- Deliver AI features from prototype through production across Python or TypeScript AI services and React, Vue, or Next.js frontends.
- Partner with stakeholders and engineering leadership to measure impact and iterate on production tools.
- Extend reusable architectures to support new use cases through configuration.
- Stay current with GenAI, NLP, ML, IR, and cloud infrastructure best practices.

Requirements
- Bachelor's or Master's degree in Computer Science, Engineering, Data Science, or a related STEM field, or equivalent work experience.




- 4+ years of industry experience in machine learning engineering, AI engineering, or a related software engineering role.
- Strong Python and/or TypeScript/Node.js programming skills for building AI services and consuming interfaces.
- Hands-on experience deploying LLMs in production, building automated evaluation pipelines, and architecting tool-calling multi-agent systems with long-term memory.
- Practical experience with LangChain and its ecosystem, including LangGraph and LangSmith, or comparable agent-orchestration frameworks.
- Production experience with RAG architectures and vector databases.
- Full-stack capability with frontend frameworks such as React or Vue and backend cloud services such as AWS or GCP.
- Experience with Vertex AI or equivalent multi-model cloud AI platforms is preferred.
- Familiarity with Braintrust, LangFuse, or MCP-based prompt-management and observability system

📌 AI Engineer (España)
🏢 Wizeline
📍 España