Mid AI Engineer

• 3+ years in software engineering, with at least 1 year of hands-on experience building and deploying LLM-based applications in production.

• Deep proficiency in Python (including async programming, testing, and modern frameworks like FastAPI and Pydantic).

• Experience with orchestration tools such as LangGraph, CrewAI, or Vertex AI Agent Builder.

• Deep understanding of how to manage conversational state and memory in complex, non-linear AI graphs, cycles, nodes, and edges.

• Ability to treat AI engineering like software engineering, applying CI/CD, unit testing for prompts, structured logging, and observability.

• Professional fluency in English and Spanish.

• Experience with LangChain/LangGraph.

• Experience with prompt engineering and optimization.

We are looking for a Mid-Level AI Engineer to accelerate our AI engineering efforts at our Barcelona offices. We want someone with an "agentic" mindset who views LLMs as reasoning engines within a larger architecture, rather than simple text predictors.

Working closely with our AI and Engineering leadership, you will help build advanced AI systems that move beyond standard chat interfaces. Your primary focus will be architecting agentic workflows, governing complex states in LLM systems, and making sure our generative capabilities remain reliable, steerable, and scalable.

• Design and implement complex, multi-step AI workflows using Langchain/LangGraph to manage state, loops, and conditional logic.

• Develop, test, and version-control advanced prompts, Few-shot, Chain-of-Thought, ReAct.

• Build and maintain Retrieval-Augmented Generation, RAG, pipelines, including document parsing, embedding optimization, and vector database management.

• Establish automated evaluation frameworks to measure hallucination rates, groundedness, and relevancy.