In this role you will design and deploy scalable GenAI solutions and manage end-to-end RAG pipelines in production. You will work within the Data & AI team to translate client needs into robust AI architectures using cloud-native tools. You’ll integrate foundational models from providers like OpenAI and Bedrock, collaborating with cross-functional teams to operationalize models at scale. This position offers hybrid work across Spain with opportunities to influence AI strategy and delivery in client engagements. Health, life, and accident insurance Flexible compensation and stock purchase plans Versátil schedules and vacation policies Personalized training paths Sustainability programs Diversity networks Design and deploy end-to-end AI solutions using LLMs, LangChain/LangGraph, and cloud-native tools Develop and manage RAG pipelines: ingestion, chunking, embeddings, vector storage, retrieval,
and generation Integrate foundational models from platforms like Amazon Bedrock and OpenAI Collaborate with cross-functional teams to define architecture and productionize AI models Monitor and optimize performance of deployed models and pipelines 3+ years of hands-on AI experience Experience with LangChain or LangGraph for GenAI orchestration Deep understanding of LLM fundamentals: Transformers, attention, embeddings, tokenization Proficiency in at least one cloud platform (AWS, Azure, or GCP) Experience with Azure AI Studio or Amazon Bedrock Strong experience with RAG pipelines and OpenAI APIs Familiarity with ML libraries: scikit-learn, Pandas, Numpy Excellent communication skills in English (B2/C1) clear communication cross-functional collaboration problem-solving mindset LangChain LangGraph