Engenheiro de IA Sênior

This position is listed on behalf of a partner company, which manages all applications and next steps. Our partner is looking for an Engenheiro de IA Sênior based in Brazil. Join a technology-driven environment where you will design and build intelligent applications powered by Large Language Models (LLMs). As a Senior AI Engineer, you will lead the development of scalable, production-ready solutions, including chatbots, copilots, and autonomous AI agents. You will work with advanced AI APIs, retrieval-augmented generation architectures, and modern cloud technologies to deliver reliable, secure, and high-performing systems. Your expertise will help optimize model orchestration, improve response quality, and balance performance with operational costs. Collaborating with engineering and analytics teams, you will identify technical bottlenecks and establish robust practices for monitoring and continuous improvement. This remote opportunity is ideal for an experienced engineer who combines hands-on technical expertise with a strong focus on scalability, security, and software quality. Accountabilities - Design, develop, and maintain intelligent applications powered by LLMs, including chatbots, copilots, and autonomous AI agents. - Integrate and orchestrate APIs from AI model providers, including OpenAI, Anthropic, and other relevant platforms, to deliver effective and scalable AI-powered solutions. - Architect and implement Retrieval-Augmented Generation (RAG) pipelines, managing embeddings, vector search, contextual information, and conversational memory. - Develop robust back-end services using Python or Node. js, integrating REST APIs, microservices, and supporting infrastructure. - Implement guardrails, response validation mechanisms, and AI security controls to improve output reliability and protect applications against threats such as prompt injection and context manipulation. - Optimize model performance, response latency, token consumption, and infrastructure costs while maintaining high standards of reliability and user experience.

- Establish monitoring, logging, tracing, and observability practices to track the performance and behavior of LLM-powered systems in production. - Deploy and manage applications in cloud environments such as AWS, Google Cloud Platform (GCP), or Microsoft Azure, using Docker and appropriate deployment practices. - Apply CI/CD principles to streamline development, testing, deployment, and ongoing maintenance. - Collaborate with engineering, analytics, and other technical teams to identify bottlenecks, investigate incidents, and implement effective solutions. - Promote scalable architecture, maintainable code, and engineering best practices throughout the AI application lifecycle. - Proactively identify opportunities to improve system architecture, security, performance, and operational efficiency. Requirements - Strong experience designing, developing, and deploying applications based on Large Language Models (LLMs), including chatbots, copilots, and AI agents. - Proficiency in back-end development using Python or Node. js, with a solid understanding of REST APIs, microservices, and distributed application architectures. - Practical experience integrating and orchestrating APIs from LLM providers such as OpenAI, Anthropic, or comparable services. - Knowledge of Retrieval-Augmented Generation (RAG), vector embeddings, conversational memory, context management, and semantic search. - Familiarity with frameworks such as LangChain or equivalent tools for building and orchestrating LLM-powered applications. - Experience working with vector databases and search technologies, such as Chroma, OpenSearch, or similar solutions. - Understanding of AI security practices, including protection against prompt injection, context control, response validation, and the implementation of guardrails. - Experience with Docker and cloud platforms such as AWS, GCP, or Azure.