AI Engineer – Agentic Workflows (Node.js/React)

Cloudfide builds and evolves large-scale Big Data and cloud-native platforms for global clients, including leaders in retail and the Fortune 500. They operate fully in the cloud ecosystem and work with the latest technologies including AI, ML, MLOps, and modern data architectures. The company focuses on delivering solutions that have measurable real-world impact and empower data-driven decision-making.

• Experience designing and building AI agents and agentic workflows, preferably with GitHub Agentic Workflows.
• Strong understanding of core LLM concepts, such as prompting, context windows, tool/function calling, RAG, and evaluation.
• Experience developing and maintaining custom AI agents, custom skills, tools, and integrations.
• Hands-on experience with Model Context Protocol (MCP) servers.
• Solid software engineering background with practical experience in Node.js and React.
• Familiarity with Git, CI/CD pipelines, and modern development workflows.
• Proactive and curious mindset, comfortable working in dynamic, fast-evolving project environments.
• Fluent English communication, able to collaborate effectively across international teams.

Nice to have:

• Experience with Python, especially FastAPI.
• Experience with Vue.js.
• Familiarity with MS Azure services.
• Knowledge of security best practices for LLM-based applications.

• Designing, building, and maintaining AI agents and agentic workflows, including those based on GitHub Agentic Workflows.
• Developing custom agent skills, tools, and integrations with internal and external systems.
• Building and maintaining Model Context Protocol (MCP) servers to connect agents with data sources and services.
• Applying core LLM concepts (prompt and context engineering, tool calling, retrieval, evaluation) to deliver reliable, high-quality agent behavior.
• Developing backend services in Node.js and user-facing components in React to support and expose agent capabilities.
• Translating business requirements into well-structured technical tasks and delivering features end-to-end.
• Monitoring, testing, and iterating on agent performance, quality, cost, and safety.
• Conducting code reviews and contributing to documentation and best practices.
• Sharing knowledge about AI tooling and agentic patterns, contributing to a collaborative learning culture within the team.