Generative AI Engineer (Spanish)

About the role

We are looking for a technically proficient Generative AI Engineer to design, develop, and maintain AI‑powered solutions that support business needs across multiple domains. The role involves building scalable GenAI applications, implementing Retrieval‑Augmented Generation architectures, and integrating Large Language Models into enterprise ecosystems.

Key responsibilities

• Analyze business requirements and translate them into AI‑powered solutions such as assistants, chatbots, copilots, and autonomous agents.
• Design, develop, test, and deploy Generative AI applications and Retrieval‑Augmented Generation (RAG) architectures, including data ingestion, indexing, and response generation.
• Orchestrate LLM workflows using frameworks like LangChain, LangGraph, and MCP, and integrate AI services with APIs, databases, and enterprise applications.
• Optimize prompts, retrieval strategies, and model interactions to improve response quality and business value.
• Implement evaluation frameworks to measure AI performance, reliability, and user satisfaction while ensuring compliance with security and responsible AI standards.

Required profile

• Strong expertise in Generative AI concepts, Large Language Models, and prompt engineering.
• Experience designing AI assistants, chatbots, copilots, and agent‑based solutions.
• Proficiency in Python development and building production‑grade applications and APIs.
• Ability to work autonomously, collaborate with cross‑functional teams, and communicate effectively with business and technical stakeholders.

Required skills

• Python
• Large Language Models (LLMs) and prompt engineering
• LangChain, LangGraph, MCP
• Retrieval‑Augmented Generation (RAG) techniques: document ingestion, chunking, embedding, indexing, semantic and hybrid search
• Vector databases (FAISS, ChromaDB, Pinecone, Azure AI Search)
• SQL and REST APIs
• Git, Azure DevOps, Docker
• Cloud platforms (Azure, AWS) and CI/CD pipelines