AI Engineer

Workana is the largest remote work platform for talent in Latin America. Our division focuses on matching exceptional professionals with leading and innovative companies around the globe. About the client Our client is an innovative company developing enterprise-grade solutions to automate business processes and connect AI capabilities with enterprise data. We are looking for an experienced AI Engineer to join the engineering team and build reliable, scalable AI-powered applications. This is a fully remote opportunity for professionals based in Latin America, working closely with an international team in an English-speaking environment. Role overview As an AI Engineer, you will design, build, and deploy enterprise AI applications using Python, C#, and Microsoft Azure. You will turn technical designs into production-ready solutions, integrating LLMs, retrieval-augmented generation (RAG) pipelines, and AI agent workflows with enterprise data and backend systems. We are looking for an engineer who can work autonomously in a remote environment, translate technical designs into functional systems, collaborate effectively with cross-functional international teams, and communicate fluently in English. Selection process The process usually consists of 4 stages and takes on average 4-6 weeks to be completed depending on eventual additional technical rounds or take home tests. • Initial interview with recruiting team; • Technical interview with client; • Cultural fit interview with client's manager; • Final interview with C-level. As Workana has multiple clients, if you pass the 1st round with Workana's recruiting team, you will be eligible to be presented to different clients in case the 1st one doesn't succeed. Responsibilities • Build and maintain enterprise AI-powered applications and backend services using Python and C#. • Integrate Large Language Models (LLMs) and generative AI capabilities into business process workflows. • Develop and optimize RAG pipelines connecting LLMs with enterprise knowledge bases and structured or unstructured data. • Implement AI agents, tool-calling capabilities, and orchestrated workflows to automate complex business tasks. • Design and develop secure REST APIs and microservices using FastAPI, C#, and .NET. • Build, containerize, and deploy cloud applications using Microsoft Azure (Azure AI Foundry, Blob Storage, Container Apps, AKS) and CI/CD automation. • Evaluate AI outputs, improve retrieval quality, troubleshoot issues, and optimize latency, reliability, and cloud resource consumption. • Collaborate with AI architects, data scientists, and engineering teams to translate architecture designs into reliable deliverables. Requirements • Strong professional software engineering experience with Python and C#. • Hands-on experience developing REST APIs, backend services, and microservices architectures. • Solid experience with cloud-based development and containerized deployments, preferably on Microsoft Azure. • Proven experience with generative AI, LLM integration, and frameworks such as LangChain, Semantic Kernel, or similar. • Practical knowledge of RAG architecture, embeddings, vector search, and data retrieval pipelines. • Strong understanding of software engineering best practices, CI/CD pipelines, automated testing, and secure coding. • Strong analytical, troubleshooting, and problem-solving skills with the ability to work independently. • Advanced English proficiency (C1) is mandatory, as the role involves active technical discussions and international collaboration. • Must be based in Latin America. Bonus points • Experience with frontend development and UI integration using React and TypeScript. Benefits • Compensation in USD • Fully remote work within Latin America with flexible time schedules • Career growth with international clients and dynamic projects • This is a long-term independent contractor agreement with no additional benefits such as paid time off, health insurance, etc.