




Job Summary: Join the company’s transformation by making a difference through real business challenges leveraging data, with direct impact on customers and business outcomes. Key Highlights: 1. Prototype and program GenAI-based agents and conversational flows. 2. Design architectures for flows, routers, nodes, and 'tools' for AI agents. 3. Proficiency in prompt engineering and data-driven model evaluation. MISSION Join the company’s transformation and make a difference through real business challenges leveraging data, with direct impact on customers and company outcomes. JOB RESPONSIBILITIES Prototype and program GenAI-based agents and conversational flows Define guardrails and technical safety criteria for agent behavior, coordinating with Legal, Regulatory Compliance, Legal Advisory, and Information Security. Design architectures for flows, routers, nodes, 'tools', and data structures for AI agent handover and reporting Implement and integrate new workers and agents into the agent architecture Define required 'prompts' and 'tools' for end-to-end flow execution Define Responsible AI (RAI) tests to be performed Program and execute large-scale automated tests based on Golden Data Sets designed for Responsible AI testing Update and correct 'prompts' and 'tools' in response to operational or business-context changes, ensuring traceability alongside models and pipelines Perform controlled deployment of enhancements and fixes in the PRE environment Proactively adjust guardrails in response to regulatory changes Update technical documentation with implemented improvements REQUIREMENTS **Desired Experience:** Knowledge in data science, data engineering, artificial intelligence, data analysis, and related tools. Familiarity with Data Science technologies and tools (Python, R, SQL, etc.). Ability to understand and evaluate data models and algorithms. Backend development in Python (FastAPI, async) and LLM orchestration frameworks Experience with CI/CD, containers, orchestration, and security best practices Knowledge of MCP and A2A (Agent-to-Agent). Understanding of artificial intelligence regulation. Experience developing RAG (Retrieval-Augmented Generation) agents Ability to evaluate and generate test suites to assess changes in prompts, models, or tools. Knowledge of prompt-injection techniques, information leakage, and red-teaming methods. Experience integrating with tools and APIs (tool calling). Knowledge of version control and change management systems enabling versioning of prompts, tools, and test datasets. **Required Knowledge:** Experience designing conversational flows and LLM-based applications Proficiency in prompt engineering and data-driven model evaluation Ability to conduct A/B testing and document technical processes Proficiency with relational and in-memory databases Programming and scripting knowledge **Skills:** Coordinate testing with business teams Ability to log and review what occurred in each conversation Communication and presentation skills Presentation handling and task coordination Teamwork capability Report writing Collaborative mindset: we are driving the Artificial Intelligence area across the entire group. You will collaborate with individuals of diverse profiles and experience levels to develop the optimal solution delivering business impact. At SANTA LUCIA S.A., Cª SEGUROS, we work to ensure real and effective equal opportunities, promoting professional development and workforce diversity, aligned with our commitment to UN Agenda 2030 Sustainable Development Goal 5 (Gender Equality). **Province:** Madrid **Company:** SANTALUCIA SEGUROS **Date:** Mar 5, 2026


