ML Platform Engineer

Let me introduce... With Sonia, doctors are successful doctors. We create and deploy AI enhanced solutions that make doctors’ lives easier, patients’ care better, and healthcare systems more efficient. If you’re an intrinsically motivated self-starter who values impactful work, join us in revolutionizing healthcare.We’re looking for an experienced ML Platform Engineer (all) with deep Kubernetes expertise to support the infrastructure powering our AI and ML workloads.You’ll work closely with ML engineers on everything from deploying cutting-edge LLM inference to refining observability and automating workflows—always with reliability, scalability, and performance as your guiding principles.This role can be performed remotely from anywhere in Germany or Luxembourg, or in a hybrid setup from our offices in Luxembourg or Berlin. This is what you’ll own Support and enhance our Kubernetes-based infrastructure in cloud environments, running both ML/LLM workloads and general applicationsDeploy and optimize LLM inference systemsDesign, build, and improve MLOps/DevOps pipelines to support the entire development lifecycleManage GPU scheduling and autoscaling with Kubernetes-native toolingEnsure observability and alerting across the platformOperate and troubleshoot supporting infrastructureContribute to platform reliability, security, and performance through automation and best practices You’ll thrive in this role if you bring 5+ years of experience in MLOps or SREStrong hands-on Kubernetes experience, including GitOps (Flux or ArgoCD), Kustomize, Helm and production troubleshootingFamiliarity with LLM inference deployment and optimization in Kubernetes (e.g., vLLM, LMCache, llm-d)Experience with MLOps supporting tools such as MLflow or Argo WorkflowsUnderstanding of GPU resource orchestration in Kubernetes environmentsProfound knowledge of observability tools, such as VictoriaMetrics, VictoriaLogs and GrafanaKnowledge of database and broker administration (PostgreSQL, Redis and RabbitMQ)Solid scripting skills in PythonComfortable working with cloud platforms (OVHcloud, AWS, GCP or Azure)Nice-to-HavesExperience with audio ML models or real-time inferenceExposure to CI/CD practices tailored for ML systemsFamiliarity with Kubernetes networking, security, or performance tuning Why you’ll love working with us Full ownership of a mission-critical platformA team that values curiosity, learning, and experimentationRemote-first setup with the option to work in our Berlin officeCompetitive salary depending on experienceWork on AI infrastructure that directly impacts healthcare innovation Ready to apply? If you're passionate about web development and want to work with cutting-edge technologies, we'd love to hear from you!I'm Margarita and will be guiding you through the application process.