About metalsa metalsa is a global company specialized in structural products and integrated chassis systems for the light and commercial vehicle markets. With more than 60 years of experience, we deliver innovative, high-quality solutions that support the future of mobility. Our purpose is to deliver the best chassis solutions that drive the future forward. Position summary we are seeking a senior ai software engineer – agentic systems to lead the design and development of ai-powered solutions that enable business process transformation through agentic ai. This is not another saas role: you will connect ai agents to real manufacturing, supply chain, and engineering systems at global scale, transforming how a leading industrial company operates. This role combines hands-on software engineering, ai agent architecture, and technical leadership. Reporting to innovación co., metalsa’s innovation organization, you will work closely with product teams and process experts to redesign future-state workflows and build scalable, production-grade ai solutions that integrate with enterprise systems and data sources. The ideal candidate has strong software engineering foundations, practical experience building ai applications in production, and expertise with llm apis, agent frameworks, rag architectures, and mcp integrations. Sr ai software engineer – agentic systems key responsibilities ai solution development design, develop, and maintain ai-powered applications and agent-based solutions, from business requirements through production. Build production-ready ai agents capable of orchestrating workflows and interacting with enterprise systems. Develop integrations between ai agents and internal platforms using mcp and related integration patterns. Design and implement retrieval-augmented generation (rag) solutions leveraging enterprise knowledge sources. Create reusable ai components, tools, and frameworks that accelerate future development. Evaluation, safety & responsible ai own the evaluation strategy for ai systems: define quality metrics, build eval pipelines, and monitor agent behavior in production. Implement guardrails and safety mechanisms for agentic workflows, ensuring alignment with data governance and responsible ai practices for enterprise integrations. Technical leadership provide technical guidance and mentorship to software engineers and technical contributors. Conduct code reviews and promote engineering best practices. Support architectural decisions and help define technical standards for ai development across the organization. Platform & scalability deploy and maintain ai applications in cloud environments. Ensure reliability, scalability, security, and performance of ai solutions across business functions. Required qualifications education bachelor’s degree in computer science, software engineering, information technology, or a related field. Experience 7 years of software engineering experience. 2 years developing generative ai or llm-based applications. 1 year building ai agents or agent-based workflows in production environments. Experience leading technical initiatives, mentoring engineers, or acting as a technical lead. Experience scaling ai solutions beyond proof-of-concept environments into production. Required technical skills programming languages python (required). Typescript (strongly preferred). Ai & llm development hands-on experience integrating and developing solutions with llm apis from one or more major providers (e.g., openai, anthropic claude, google gemini / vertex ai). What matters is strong fundamentals — prompting, tool use, structured outputs, and context management — not a specific vendor. Agent development experience designing and developing agents using modern agent frameworks (e.g., langgraph, openai agents sdk, or equivalent) or custom-built agent systems. Integration protocols (mcp & a2a) experience building, consuming, or integrating model context protocol (mcp) servers and tools. Experience connecting ai agents to enterprise systems through mcp architectures. Familiarity with agent interoperability protocols such as a2a (agent2agent). Retrieval-augmented generation (rag) experience with: rag architectures and vector search. Knowledge retrieval systems over structured and unstructured data sources. Enterprise search solutions. Cloud & devops strong cloud fundamentals: deployment, networking, security, and scalability of cloud-native applications. Azure (preferred — our primary cloud platform); aws or gcp experience is also valued. Containerization fundamentals (docker or equivalent). Preferred qualifications experience with evaluation and observability practices for ai systems — designing eval datasets, quality metrics, and tracing/monitoring pipelines (tools such as langsmith, braintrust, or langfuse are a plus). Kubernetes exposure. Experience building reusable ai platforms or internal developer frameworks. Experience supporting enterprise-scale ai deployments.