Backend Engineer, AI Integrations

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Backend Engineer, AI Integrations based in Brazil. This role offers the opportunity to lead engineering work on production-ready AI products and bring generative AI features from concept to reliable customer-facing solutions. You will architect backend systems, write clean and scalable code, integrate modern LLM APIs, and own features throughout the development lifecycle. The position sits at the intersection of strong full-stack engineering and practical AI application development, with a focus on model APIs, retrieval, and agentic systems. You will work on varied client projects while also contributing to internal AI tooling and engineering practices. Beyond hands-on development, you may mentor engineers, contribute to hiring, and help shape technical delivery standards. This is a fully remote, flexible environment that values ownership, continuous learning, collaboration, and measurable outcomes. This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Backend Engineer, AI Integrations based in Brazil. This role offers the opportunity to lead engineering work on production-ready AI products and bring generative AI features from concept to reliable customer-facing solutions. You will architect backend systems, write clean and scalable code, integrate modern LLM APIs, and own features throughout the development lifecycle. The position sits at the intersection of strong full-stack engineering and practical AI application development, with a focus on model APIs, retrieval, and agentic systems. You will work on varied client projects while also contributing to internal AI tooling and engineering practices. Beyond hands-on development, you may mentor engineers, contribute to hiring, and help shape technical delivery standards. This is a fully remote, flexible environment that values ownership, continuous learning, collaboration, and measurable outcomes. Accountabilities: Lead engineering efforts for AI-powered products, taking features from early concepts and prototypes through production-ready implementation. Architect and develop robust backend systems using TypeScript or Python, with an emphasis on clean, maintainable, and scalable code. Integrate modern LLM APIs and build production-grade generative AI capabilities into customer-facing applications. Design and implement agentic systems, including agent orchestration, tool use, prompt engineering, and AI workflows. Build and maintain retrieval capabilities using approaches such as RAG, embeddings, and vector search. Evaluate and apply different LLMs according to task requirements, balancing quality, performance, cost, and other relevant considerations. Create and integrate MCP servers and transform API endpoints into usable tools for AI-powered systems. Work with cloud infrastructure and databases to support reliable and scalable AI applications. Own features end-to-end and collaborate closely with teammates to transform customer and client ideas into dependable products. Improve internal AI tooling, engineering workflows, and delivery practices. Accurately assess project scope, estimate timelines, and communicate progress and potential risks. Support team growth by participating in technical interviews and helping identify future engineering talent. Mentor and support other engineers, sharing knowledge and helping raise overall technical capability. Contribute to a culture of ownership, continuous improvement, experimentation, and customer-focused problem solving. Requirements 5+ years of professional software engineering experience, including experience leading projects or people. Strong backend development experience with TypeScript or Python . Experience working with cloud infrastructure such as AWS, Azure, or GCP . Experience with databases such as PostgreSQL, MongoDB , or comparable technologies. Hands-on experience building products with modern LLM APIs, including platforms such as OpenAI or Anthropic. Practical experience developing agentic products and applying prompt engineering techniques. Experience with retrieval technologies and architectures, including RAG, embeddings, and vector search. Experience writing and evaluating Claude Skills. Strong understanding of how to select appropriate LLMs for different use cases while balancing quality, cost, and other technical considerations. Experience creating and integrating MCP servers and converting API endpoints into AI-accessible tools. Demonstrated growth mindset and ability to quickly learn new programming languages, frameworks, technologies, and methodologies. Strong written and verbal communication skills in English. Ability to accurately estimate scope and timelines and communicate expectations effectively. Experience using AI-assisted coding tools such as Claude Code or Codex. Nice to have: Experience with system administration, internal workspaces, and IT infrastructure, including Microsoft 365, Google Workspace, or SharePoint. Nice to have: Experience connecting Cowork or ChatGPT Work to internal data sources. Nice to have: Experience integrating Microsoft 365 with AI systems. Nice to have: Experience building data ingestion pipelines. Nice to have: Experience working in the financial sector. Bonus: Consulting, product studio, or multi-client delivery experience. Bonus: Personal, open-source, side, or professional projects that demonstrate your ability to build and ship technology. Benefits Fully remote position based in Brazil. Flexible working hours focused on results and output rather than time spent online. Strong emphasis on work-life balance across different stages of life. Annual salary range of US$60,000–US$100,000 , with exact compensation determined based on individual qualifications and alignment with the role. Opportunity to work on varied AI-powered products and cutting-edge generative AI applications. Exposure to modern LLMs, agentic engineering, retrieval systems, MCP, and AI-assisted development. Opportunities to contribute to internal AI tools and improve engineering and delivery practices. Opportunity to participate in hiring and mentor other engineers. Supportive and collaborative culture that encourages experimentation, learning, and continuous improvement. High level of ownership and autonomy in a startup-style environment. Inclusive workplace that values individual strengths, different perspectives, and ongoing professional growth. Opportunity to work directly on technology designed to solve meaningful customer and client problems. How Jobgether works: We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best! Why Apply Through Jobgether? Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time. #LI-CL1