EG - Agentic AI Engineer

Role overview A hands-on engineering role within an AI-focused pod model, responsible for designing, building, and deploying production-grade AI agents and agentic workflows. The work centers on orchestrating autonomous systems using leading LLM frameworks, Retrieval-Augmented Generation (RAG), and Model Context Protocol (MCP) to connect AI capabilities with enterprise software ecosystems and data sources on AWS.

Responsibilities - Develop production-grade AI agents, state management mechanisms, and multi-agent workflows using frameworks such as LangGraph, CrewAI, or Agent Development Kit (ADK). - Connect AI agents to enterprise tools, APIs, and external platforms via Model Context Protocol (MCP) and structured function calling. - Build and maintain high-performance RAG pipelines using vector databases like Pinecone or Weaviate, applying semantic search, chunking, and grounding strategies. - Run automated evaluations, regression tests, task-success metrics, and safety guardrails that defend against prompt injection and sensitive-data exposure. - Deploy LLM applications on AWS using Amazon Bedrock and observe them with platforms such as LangSmith, Langtrace, or AgentOps to troubleshoot failures and tune performance. - Write clean, testable Python code, keep thorough technical documentation, and collaborate with senior engineers, MLOps, and product teams across the full AI development lifecycle.

Requirements - Three or more years of professional software development experience with direct, hands-on work building LLM-based, RAG, or agentic AI applications. - Advanced Python skills and practical experience with AWS (especially Amazon Bedrock), agentic frameworks (LangGraph, CrewAI, or ADK), vector databases (Pinecone, Weaviate), and Model Context Protocol (MCP). - Hands-on experience testing, evaluating, and monitoring LLM execution using tools such as LangSmith, Langtrace, or AgentOps. - Strong ownership mindset, troubleshooting ability, and a collaborative approach to delivering quality software within cross-functional teams. - Advanced written and spoken English.

Nice to have - Exposure to multi-agent systems and reinforcement learning concepts. - Experience building front-end AI interfaces with Chainlit, Streamlit, or React. - Familiarity with MLOps platforms such as MLflow or Kubeflow. - Exposure to secondary cloud ecosystems like Azure AI or Google Cloud Platform.

Benefits and work setup - 100% remote position based anywhere in Latin America. - Local national holidays off, generous paid time off, and financial support toward health insurance. - Competitive USD compensation pegged to the U.S. dollar and ongoing growth opportunities on high-impact global projects.