AI/ML Platform Engineer - Brazil (Remote)

AI/ML Platform EngineerLocation: Brazil Employment Type: Contract Work Model: RemoteRole OverviewWe are seeking an experienced AI/ML Platform Engineer to design, build, and maintain scalable AI/ML infrastructure and delivery platforms. The ideal candidate will have hands-on experience supporting GPU workloads, LLM integrations, Kubernetes, Docker, Helm, AWS, Terraform/Ansible, CI/CD, and DevOps tooling. Key ResponsibilitiesDesign and engineer scalable infrastructure for AI/ML workloads and GPU-based environments.Build and maintain platforms supporting LLM applications and integrations.Deploy and manage AI/ML workloads using Kubernetes, Docker, and Helm.Develop and maintain CI/CD pipelines for ML models, applications, and infrastructure.Automate infrastructure provisioning and configuration using Terraform and Ansible.Deploy and manage AI/ML infrastructure on AWS.Implement monitoring, logging, security, and performance optimization for AI/ML platforms.Support model deployment, integration, scaling, and operationalization.Troubleshoot infrastructure, container, Kubernetes, and deployment issues.Establish DevOps and MLOps best practices for reliable AI/ML delivery.Collaborate with data scientists, ML engineers, software engineers, and DevOps teams.Required SkillsStrong experience as an AI/ML Platform Engineer, MLOps Engineer, or DevOps Engineer supporting AI/ML platforms.Hands-on experience with:KubernetesDockerHelmAWSTerraform and/or AnsibleCI/CDGPU workloadsLLM integrationsStrong understanding of cloud infrastructure, containers, orchestration, and automation.Experience building scalable and highly available AI/ML platforms.Strong scripting and automation skills.Knowledge of monitoring, logging, security, and infrastructure optimization.Preferred SkillsExperience with MLOps platforms and practices.Experience with NVIDIA GPU infrastructure and CUDA environments.Knowledge of Python and AI/ML frameworks.Experience with LLM platforms, model serving, and inference workloads.Familiarity with AWS services such as EKS, EC2, S3, and SageMaker.Experience with Prometheus, Grafana, or similar observability tools.