Desenvolvedor(a) 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 a Desenvolvedor(a) de IA – Sênior based in Brazil. Take the lead in designing and building innovative artificial intelligence solutions that transform business needs into scalable, intelligent products. In this senior role, you will combine expertise in AI architecture, Generative AI, and full-stack development to deliver end-to-end applications powered by Large Language Models (LLMs). You will work with modern technologies to develop conversational systems, orchestrate AI agents, and integrate intelligent capabilities into enterprise environments. Beyond hands-on engineering, you will influence technical strategy, contribute to product roadmaps, and guide architectural decisions. As a technical reference for the team, you will mentor developers, promote engineering excellence, and help establish best practices. This remote opportunity is ideal for an experienced professional who thrives on complex challenges, technical autonomy, and the opportunity to turn emerging AI capabilities into practical business solutions.

Lead the end-to-end development of AI solutions, from requirements discovery and technical planning to architecture design, implementation, deployment, and ongoing maintenance. Define scalable AI architectures, model integration strategies, and data pipelines that support reliable, efficient, and production-ready applications. Design, develop, and integrate Generative AI capabilities and Large Language Models (LLMs) into products, applications, and enterprise systems. Build full-stack applications using React and JavaScript for front-end development and Python for back-end services and AI integrations. Develop advanced conversational solutions capable of understanding context, interpreting user needs, maintaining coherent interactions, and directing conversations appropriately. Design, implement, and integrate AI agents that execute tasks sequentially and collaboratively, including multi-agent orchestration and agentic workflows. Develop and maintain integrations between applications, APIs, language models, data sources, and enterprise systems. Implement Retrieval-Augmented Generation (RAG), Natural Language Processing (NLP), and other relevant AI techniques to improve the accuracy, relevance, and effectiveness of intelligent applications. Integrate AI solutions with cloud environments and enterprise infrastructure, ensuring scalability, performance, maintainability, and operational reliability. Establish and promote engineering best practices through code reviews, model evaluations, technical documentation, and continuous improvement of development processes. Mentor team members, share technical knowledge, and serve as a technical reference for AI architecture, full-stack development, and implementation decisions. Collaborate with product and business stakeholders to translate requirements into technical solutions, contribute to product roadmaps, and align implementation strategies with business objectives. Work hands-on throughout the development lifecycle, supporting the evolution, optimization, troubleshooting, and long-term sustainability of deployed solutions. Requirements Strong proficiency in Python and experience with advanced AI and machine learning frameworks and tools, such as LangChain, Hugging Face, and MLflow. Demonstrated experience with Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Natural Language Processing (NLP). Solid full-stack development experience, including front-end development with React and JavaScript and back-end development with Python. Practical experience integrating LLMs into production applications and products, with an understanding of the technical considerations involved in deploying AI-powered features. Knowledge of AI agents, agentic workflows, multi-agent orchestration, and the development of systems that coordinate multiple intelligent components. Experience designing and implementing APIs, application integrations, and connections between AI models and enterprise systems. Familiarity with cloud platforms such as AWS, Google Cloud Platform (GCP), or Microsoft Azure. Knowledge of containerization and orchestration technologies, particularly Kubernetes, as well as CI/CD pipelines and modern software delivery practices. Understanding of AI architecture, data pipelines, model integration, and the principles required to develop scalable and maintainable intelligent applications. Strong analytical and problem-solving skills, with the ability to evaluate technical alternatives and connect engineering decisions to business objectives. Ability to understand business needs, contribute to solution planning, define appropriate technical approaches, and lead implementation through delivery. Senior-level autonomy, initiative, accountability, and sound technical judgment when handling complex projects and ambiguous requirements. Excellent communication and collaboration skills, including the ability to explain technical concepts, mentor colleagues, conduct code reviews, and act as a technical leader within project teams. A hands-on mindset and willingness to contribute directly to architecture, coding, integrations, testing, deployment, and ongoing solution improvement. Benefits Remote work: Work from home in Brazil, with no regular office attendance specified in the job description. Technical leadership: Take ownership of strategic AI initiatives and influence architectural decisions, implementation standards, and technical direction. Cutting-edge technologies: Work with Generative AI, LLMs, RAG, conversational AI, intelligent agents, and modern full-stack development tools. End-to-end project ownership: Participate in the complete solution lifecycle, from understanding business needs and planning architectures to implementation and maintenance. Professional growth: Expand your expertise in AI engineering, cloud technologies, multi-agent systems, and scalable enterprise applications. Mentorship opportunities: Share knowledge, support team development, and establish yourself as a technical reference in AI and software engineering. Business impact: Build intelligent products that address real-world challenges and connect advanced AI capabilities with practical business objectives. Collaborative environment: Work across technical and product disciplines, contributing to roadmap planning and strategic implementation decisions. Compensation and additional benefits: Salary, healthcare coverage, paid leave, bonuses, equipment allowances, and other employment benefits are not specified in the available job description and should be confirmed during the recruitment process.