AI Engineer (Generative AI / LLMs / RAG) – Python / LangChain – Remote (Spain)

Description At The Whiteam Consulting, we are looking for an AI Engineer to participate in the development of an AI-based platform that automates legacy code analysis, technical documentation generation, and architecture proposals using LLM models. We are looking for a profile with experience in Generative AI, RAG, and agent development, capable of designing, building, and optimizing scalable AI solutions in production environments, collaborating with multidisciplinary teams and acting as a technical reference within the project. Responsibilities Development of LLM-based AI agents. Design and implementation of RAG pipelines. Integration with OpenAI APIs and cloud AI platforms. Development of solutions using Python, LangChain, and/or LangGraph. Optimization and scaling of models in production. Automatic documentation generation and code analysis. Participation in technical decisions and the evolution of the AI architecture. Researching new technologies and trends in GenAI. Technical documentation and knowledge transfer to the team. Requirements 3+ years of experience in Artificial Intelligence. Solid experience in: Python, LangChain or LangGraph, OpenAI APIs, RAG architectures. Deep knowledge of: Transformers, Embeddings, Tokenization, Attention Mechanisms. Experience with at least one cloud platform: AWS, Azure, GCP. Experience with: Azure AI Studio or Amazon Bedrock. B2/C1 English. Responsible AI and Guardrails will be valued. Amazon SageMaker. Weekly...