ppIn this role you will design, build and operate TXT Group's AI and application platform, ensuring secure, scalable environments for enterprise apps and AI/ML workloads. You will own cloud-native platforms, Kubernetes clusters, CI/CD pipelines and AI infrastructure, collaborating with software and AI engineers to deliver reliable, observable services. You’ll optimize costs, security and performance while enabling rapid experimentation and production readiness. This is a hands-on, cross-functional role at the core of the company’s AI initiatives. /pulliCareer opportunities in a fast-growing, international environment /liliContinuous training on technical topics /liliHealth insurance /liliWelfare services /liliDesign and manage cloud-native platforms, Kubernetes clusters and containerised applications /liliBuild and maintain CI/CD pipelines and automate infrastructure provisioning and deployment /liliDesign, deploy and manage infrastructure for AI systems including LLMs, embeddings, vector databases and caching /liliDefine CI/CD pipelines for AI apps and data pipelines with reproducible environments and secure release strategies /liliManage versioning of models, prompts and configurations; support fine-tuning and retraining pipelines /liliCollaborate with software developers and AI engineers to streamline delivery and operations /liliImplement monitoring, logging, tracing and alerting for LLM applications and data pipelines /liliEnsure scalability, high availability and operational continuity of AI services /liliOptimize inference and embedding costs via sizing,



quantisation, batching and caching /liliManage secrets, API keys, access control and environment isolation for AI services /liliSupport offline evaluation and A/B testing by providing infrastructure and telemetry data /liliAt least 3 years' experience in platform and infrastructure engineering with production ownership of Kubernetes, CI/CD and cloud infra /liliSolid containerisation and orchestration skills (Docker, Kubernetes, Helm, Docker Compose) /liliProficiency with Git, GitLab CI/CD or GitHub Actions, GitOps, container registries and release management; automation in Python and Bash /liliInfrastructure as Code experience (Terraform, Ansible) on Linux /liliNetworking and security fundamentals; reverse proxies and ingress controllers (Nginx, Traefik); TLS/SSL; IAM and secrets management /liliObservability stacks (Prometheus, Grafana, Loki, OpenTelemetry, OpenSearch or ELK) in production ML/LLM environments /liliAI/MLOps tooling (MLflow, Weights Banses, model registries; model serving frameworks such as vLLM, Ollama, Triton, SageMaker or Vertex AI) /liliExperience with vector databases and embedding/RAG pipelines; PostgreSQL, SQL Server and Redis in production /liliCloud experience with at least one major provider (Azure, AWS, GCP) for ML/AI workloads /liliFamiliarity with Num2: HashiCorp Nomad is a PLUS /li /ulpIn this role you will design, build and operate TXT Group's AI and application platform, ensuring secure, scalable environments for enterpri… /p /p #J-18808-Ljbffr

📌 MLOps & Platform Engineer (Milano)
🏢 Experteer Italy
📍 Milano