Desenvolvedor(a) Sênior Full Stack - AI Engineering

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Desenvolvedor(a) Sênior Full Stack - AI Engineering based in Brazil. This is a senior full-stack engineering role focused on building a conversational AI platform for the healthcare sector. You will develop end-to-end product capabilities across Java on the backend and React on the frontend. The role combines traditional software engineering with hands-on AI application development, including LLM orchestration, prompt engineering, structured outputs, RAG, guardrails, and quality evaluation. You will help build integrations that connect conversational experiences with existing scheduling systems and third-party APIs. The product is in an early stage, creating significant space for technical autonomy, architectural input, and ownership. AI-assisted development is an integral part of the team's daily workflow, with a strong emphasis on judgment, quality, and rigorous review.

Build end-to-end product features using Java on the backend and React on the frontend, taking ownership across the full development lifecycle. Implement integrations with external scheduling APIs, including failure handling, retry mechanisms, consistency, and reliable data exchange. Design and develop conversational orchestration, defining how LLMs classify requests, extract information, generate responses, and determine when conversations should be transferred to human support. Model and evolve data persistence using both relational and non-relational databases, selecting appropriate approaches according to product and technical requirements. Develop messaging and asynchronous processing for operations that need to run independently of the active conversation. Write automated tests, participate actively in code reviews, and contribute to maintaining high engineering standards. Participate in architecture discussions and contribute technical reasoning to important product and engineering decisions. Investigate, troubleshoot, and resolve issues in production environments while maintaining system reliability. Use AI-assisted development tools thoughtfully and critically, reviewing generated code and outputs rigorously before integrating them into the product. Share technical context, collaborate closely with a small squad, and support less experienced team members through knowledge sharing and mentoring. Requirements: Solid professional experience in software development with a track record of delivering and maintaining production applications. Strong hands-on expertise with Java backend development and React frontend development , with the autonomy to work effectively across both areas. Experience with Docker and containerization , plus familiarity with deployment environments such as Azure . Strong knowledge of relational databases, including data modeling, querying, and performance optimization. Experience with non-relational databases and a clear understanding of when NoSQL approaches are appropriate. Daily experience with AI-assisted software development using tools such as Claude Code, GitHub Copilot, Cursor , or equivalent solutions, combined with sound judgment about where AI accelerates development and where human review is essential. Deep knowledge of applied AI and LLM application engineering, including prompt design, structured outputs, RAG, guardrails, and quality evaluation . Experience consuming and integrating third-party APIs. Strong autonomy, with the ability to unblock yourself while recognizing when collaboration or support is needed. A strong quality mindset balanced with pragmatism and the ability to deliver without unnecessary perfectionism. Excellent collaboration and communication skills, particularly within a small, highly interactive engineering team. Genuine curiosity about applying AI to real-world products and customer experiences. Experience with conversational platforms such as Chatwoot, Rasa, Botpress, Dialogflow , or similar tools is a plus. Knowledge of the WhatsApp Business API (WABA) , including templates, the 24-hour messaging window, and BSP integrations, is advantageous. Experience with Azure OpenAI or equivalent technologies is a plus. Experience working with healthcare products, sensitive data, and LGPD requirements is advantageous. Previous experience building products in an MVP or early-stage environment is a plus. Benefits: Fully remote work model within Brazil. Full-time employment opportunity. Opportunity to work on a new conversational AI product with direct impact on patient and healthcare experiences. Significant technical autonomy and ownership within an early-stage product environment. Hands-on exposure to modern LLM application engineering and applied AI technologies. Daily use of AI-assisted software development practices and tools. Opportunity to work across Java, React, Azure, databases, APIs, messaging, and conversational AI. Close collaboration within a small engineering squad where technical contributions and ideas are highly visible. Opportunities for knowledge sharing, mentoring, and continuous professional development. Inclusive environment that values diversity, respect, ethics, collaboration, and continuous learning. Access to learning and development initiatives, technical communities, training programs, and educational partnerships.

laptop-ats-crawler v3