AI Engineer Sênior

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a AI Engineer Sênior based in Brazil. This role focuses on designing and developing intelligent AI agents and workflows that solve complex business challenges. You will build production-ready solutions using Python, MCP-based architectures, RAG pipelines, vector databases, and modern AI services. The position combines hands-on engineering with technical architecture, reusable components, governance, and solution evaluation. You will integrate AI agents with APIs, external tools, enterprise applications, and services to support sophisticated workflows. The role also emphasizes observability, scalability, reliability, and continuous improvement across AI solutions. You will collaborate closely with engineering, architecture, and technical squads to connect AI capabilities with business processes. This is an opportunity to contribute to innovative digital transformation initiatives in a collaborative and continuously evolving environment. Accountabilities: - Design, develop, and evolve AI agents and intelligent workflows using MCP-based architectures. - Build RAG pipelines and context-retrieval mechanisms using vector databases and other retrieval technologies. - Integrate AI agents with APIs, external tools, and services to support complex business workflows. - Develop AI agents in Python, preferably using Google ADK. - Build and maintain agentic workflows using DeepAgents. - Integrate AI models and services through Vertex AI and Gemini models. - Define technical architecture patterns, reusable components, and governance guidelines for AI platforms. - Ensure strong observability across solutions through logging, metrics, tracing, and other monitoring practices. - Collaborate with engineering and technical teams to ensure consistent integration between AI agents and enterprise applications. - Design solutions aligned with business processes, integrations, technical requirements, and enterprise constraints.

- Ensure developed components are scalable, reusable, maintainable, and prepared for continuous evolution. - Define and apply validation and evaluation strategies for LLMs and AI agents using metrics and approaches such as DeepEval and LLM-as-a-Judge. - Contribute to the continuous improvement of AI engineering practices, frameworks, standards, and solution quality. Requirements: - Strong professional experience developing applications and solutions with Python. - Hands-on experience building AI agents, intelligent workflows, and integrations with Generative AI models. - Practical experience with DeepAgents. - Strong understanding of MCP-based architectures and integrations. - Experience implementing RAG pipelines and working with vector databases. - Experience integrating APIs, tools, external services, and enterprise applications. - Experience with Vertex AI and Gemini models. - Ability to define technical standards, reusable abstractions, architecture patterns, and engineering best practices. - Experience implementing observability practices, including logs, metrics, and distributed tracing. - Knowledge of LLM and AI agent validation and evaluation, including tools such as DeepEval and LLM-as-a-Judge approaches. - Strong collaboration skills and experience working with engineering, architecture, and technical squads. - Systems thinking and the ability to understand data flows, integrations, dependencies, and constraints within complex enterprise environments. - Experience with enterprise AI agent platforms is a plus. - Experience defining technical governance for AI-based solutions is a plus. - Knowledge of scalable architectures focused on component reuse is a plus. - Experience working in complex corporate environments with multiple integrations and architectural constraints is a plus.