Summary: Join as an AI Engineer (Backend) to build, deploy, and support robust AI-driven backend systems, with a strong emphasis on integrating OpenAI APIs into live environments. Highlights: 1. Design and improve backend infrastructure for AI and LLM-based applications 2. Deploy, scale, and oversee LLM-powered solutions in cloud platforms 3. Collaborate with multi-national teams on innovative projects We are looking for an AI Engineer (Backend) to join our organization. In this role, you will be responsible for building, deploying, and supporting robust AI\-driven backend systems, with a strong emphasis on integrating OpenAI APIs into live environments. You will work alongside data science, DevOps, and cloud specialists to automate deployment, monitor system health, and optimize AI\-powered processes. EPAM is a leading global provider of digital platform engineering and development services. We are committed to having a positive impact on our customers, our employees, and our communities. We embrace a dynamic and inclusive culture. Here you will collaborate with multi\-national teams, contribute to a myriad of innovative projects that deliver the most creative and cutting\-edge solutions, and have an opportunity to continuously learn and grow. No matter where you are located, you will join a dedicated, creative, and diverse community that will help you discover your fullest potential. **Responsibilities** * Design and improve backend infrastructure for AI and LLM\-based applications * Deploy, scale, and oversee LLM\-powered solutions in cloud platforms * Create and maintain CI/CD pipelines to streamline deployment activities * Oversee the performance and reliability of AI services, making necessary adjustments * Establish observability and logging frameworks to monitor LLM API usage and performance * Work in partnership with DevOps and data science teams to enhance workflow efficiency and system dependability * Leverage cloud services, with a focus on Azure, for hosting and expanding AI solutions * Develop APIs and microservices to deliver AI functionalities **Requirements** * At least 2 years of experience as a backend AI Engineer * Strong proficiency in Python backend development, particularly using FastAPI * Background in integrating and managing LLM APIs (such as OpenAI) in production settings * Understanding of prompt engineering and orchestration strategies for LLMs * Skills in mitigating LLM challenges, such as latency, cost efficiency, retries, and fallback mechanisms * Experience architecting scalable backend systems for LLM\-based APIs * Working knowledge of SQL and NoSQL databases, including Redis and Kafka * Practical experience with Databricks for data engineering and analytics * Acquainted with Model Context Protocol (MCP) for model management and integration * English language proficiency at B2\+ level or higher, both written and spoken **Nice to have** * Exposure to agentic workflows for advanced AI process automation * Knowledge of Model Context Protocol to support model interoperability **We offer** * Connectivity Bonus (25,000 ARS are paid with a salary receipt at the end of each month as a non\-wages concept). * Medicina Prepaga (It covers the collaborator and direct family group). * Paternity Leave (Two additional days are added to what is established by law, total of 4 days). * Discounts card. * English Training (English lessons, twice per week). * Training Program (Access to multiple customized training plans according to the needs of each role within the company). * Marriage bonus (The company doubles the allowance established by law that ANSES offers). * Referral Program (Referral bonus is paid when the referral of a collaborator joins the Company). * External Agreements and Discounts. * Vacations: 14 calendar days a year *By applying to our role, you are agreeing that your personal data may be used as in set out in EPAM´s Privacy Notice and Policy.*