AI Developer, Madrid

Description

AI Developer Job Description Summary Job Description **What we offer you:** We have been recognized as one of the best places to work in Spain by Forbes and the Actualidad Económica ranking, thanks to our outstanding value proposition for everyone who **joins Aegon:** We champion flexibility through our hybrid work model: you can work remotely for at least three days per week, and also spend time in offices adapted to agile methodologies. We support your work-life balance and help you disconnect, offering flexible working hours throughout the year and intensive summer working hours. The best initiatives for your physical and mental wellbeing (free health insurance, on-site physiotherapy, healthy lifestyle programs, etc.) and a wide range of social benefits and advantages (the company makes substantial contributions to your pension plan, retirement savings insurance, flexible compensation, training support, Christmas bonus, etc.). Development opportunities at all levels via cross-functional and international projects. We implement recognition programs, variable compensation for all employees, and continuous feedback. Our management model is based on regular, high-quality conversations where you play a leading role. **Culture:** 87% of our employees are proud to work at Aegon. We are an international, approachable, and empathetic company. The career opportunity of your life Would you like to help people live their best lives? That’s exactly what we do every day. We achieve this because we are a people-first company caring for people—with curiosity, connected to the world around us, and committed to leaving the world better than we found it. We continuously learn from our customers and from each other. We hope you’re as passionate about it as we are! **About the position:** Are you passionate about application development and generative AI? In this role, you will join an innovative team responsible for designing, building, and operating applications integrating generative AI and large language models (LLMs), including multimodal models. The primary focus will be enhancing IT department efficiency, robustness, and security—driving digital transformation and ensuring developed solutions are scalable and aligned with organizational objectives. * Design, build, and operate production-grade generative AI applications. * Automate processes and optimize resources to reduce costs and minimize risks across IT systems and operations. * Define best practices for LLM evaluation (tests, benchmarks, latency metrics, cost, security, etc.). * Develop solutions using workflows, agents, and other paradigms, selecting the appropriate approach for each project. * Collaborate on developing AI agents using libraries such as LangGraph or Strand Agents, applying protocols like MCP or A2A where applicable. * Integrate services and APIs while ensuring scalability, robustness, and interoperability. * Orchestrate services and data flows (events, queues, microservices) with guaranteed observability and reliability. * Select generative AI platforms and models using clear technical criteria. * Align technical solutions with strategic business initiatives. * Document, communicate, and facilitate adoption of developed solutions. **About you:** * Bachelor’s degree in Computer Engineering, Telecommunications, or related field. * Advanced English proficiency. * Strong command of Python and Java. * Experience developing applications with AI, workflows, agents, and scalable architectures. * Integration of robust APIs and services. * Ability to evaluate and compare generative AI platforms and models. **Bonus:** experience with RAGs, vector databases, agents (LangGraph/Strand), MCP/A2A protocols, cloud (AWS), and MLOps. **Common technologies:** LangChain, LangGraph, Transformers, AWS Bedrock, Azure OpenAI, FastAPI, Flask, Spring Boot, Git, Postgres\+pgvector, Qdrant, MLflow, Docker, Kubernetes, Streamlit, Gradio. Hernández García, Laura LLM, LangGraph, Strand Agents, Python, Java