ML/LLM Platform Engineer (MLOps)

Description

Job Summary: We are seeking a professional to operate infrastructure, manage costs, latency, availability, and governance, with a focus on AI service deployment and operations, observability, and data security. Key Highlights: 1. Operate and manage AI infrastructure 2. Focus on observability and data security 3. Experience with AI service deployment **About the company:** Nice to meet you—we are the people of Develcode! We are a technology company with over a decade of history, recognized as a Great Place to Work (GPTW), driven by a purpose: delivering innovative software solutions that transform businesses and people. Here, we value innovation, collaboration, and commitment, cultivating a safe, challenging, and human-centered work environment that encourages continuous growth for our employees and values the authenticity of each individual. Our team consists of highly qualified professionals distributed across Brazil, and our headquarters is located in Caxias do Sul - RS. We believe technology and people walk hand in hand, which is why we invest in learning, well-being, and purpose. Join us in building the future! **Responsibilities:** * Operate infrastructure for inference/serving and observability. * Manage costs, latency, availability, and governance of pipelines. **Technical Requirements** * Deployment and operation of AI services (in cloud and/or managed environments). * AI observability: logs, latency, cost, quality, drift (where applicable). * Data security, environment segregation, access control. * Data pipeline (basic): ingestion, preparation, versioning. **Desirable** * Experience with Bedrock/SageMaker/Vertex/Azure OpenAI (please specify). * Feature store, model registry, experiment tracking.