Senior Software Engineer - Agentic AI Development (Remote, LATAM)

ITX is Hiring a Senior Software Engineer with Agentic AI Expertise! We're looking for an Engineer with deep expertise in AI Agent development to design and implement scalable, autonomous AI systems that power exceptional user experiences. In this role, you'll focus on building on top of agentic platforms and conversational AI systems, enabling intelligent, multi-step reasoning and seamless tool integration across systems. You'll work in a multi-cloud environment, leveraging Azure and GCP to deliver dynamic AI solutions that adapt to evolving client needs. Note: This role is limited to candidates based in LATAM. Candidates from other locations will not be considered for this role. What You'll Do - Design and implement autonomous AI agents and multi-agent systems using frameworks like LangChain, LangGraph, CrewAI, or AutoGen. - Build and optimize RAG (Retrieval-Augmented Generation) pipelines, integrating vector databases (Azure AI Search, Snowflake, Pinecone, PostgreSQL) with LLMs for grounded, accurate responses. - Develop tool-use and function-calling architectures that let agents interact reliably with APIs, internal systems, and external services. - Maintain and extend the data pipelines that feed agentic workflows (e.g. ingestion, transformation, and vector-store updates), ensuring agents have access to accurate, up-to-date context. - Collaborate with data scientists and ML engineers to operationalize and fine-tune LLMs, and integrate cloud AI services (Azure AI, GCP Vertex AI) into agentic workflows. - Implement evaluation, observability, and guardrail practices for LLM-based systems, ensuring reliability, safety, and consistent behavior in production. - Design authentication and authorization handling for multi-agent systems — ensuring user identity, permissions, and access scope propagate correctly as a request moves from the orchestration layer to the specialized agents and services handling it. - Design conversational and agentic experiences (chatbots, copilots, task-automation agents) that scale across multiple channels and use cases. - Continuously evaluate emerging agentic frameworks, orchestration tools, and LLM providers to deliver best-in-class performance and cost efficiency. What We're Looking For - Agentic AI Expertise: Hands-on experience building with LangChain, LangGraph, CrewAI, AutoGen, Semantic Kernel, or comparable agent orchestration frameworks. - RAG & Retrieval: Strong understanding of vector databases, embedding models, and retrieval strategies for grounding LLM outputs. - LLM Integration: Experience working with LLM APIs (OpenAI, Anthropic, or open-source models) and cloud AI services (Azure AI, GCP Vertex AI) for deploying agents at scale. - Programming: Strong proficiency in Python, with experience designing APIs and integrating agents with existing systems and data sources. - Data Engineering (Preferred): Fundamentals or demonstrable proficiency with data pipelines and cloud data platforms (Databricks, Snowflake, BigQuery, or similar), enough to maintain and troubleshoot the data flows that support agentic and RAG systems. This is not a data engineering role — it's an AI role, and data engineering skills are desirable rather than required. - Identity & Access Management: Experience with identity and access management in distributed or service-oriented systems — token-based authentication, propagating authorization across service boundaries, and scoping what data or actions a given user is allowed to reach — applied in an agentic or multi-agent context. - Governance & Safety: Understanding of LLM evaluation, guardrails, and responsible AI practices. - Soft Skills: Analytical mindset, excellent communication, and ability to explain technical concepts to both engineers and business stakeholders. - Pace & Ways of Working: We run modern Agile — Kanban — and the pace is fast and intense. We're looking for people who thrive in that environment and collaborate close