AI Platform Engineer - Lodi

Orbyta Tech is hiring an AI Platform Engineer to join a cloud-native team working on enterprise projects that deliver AI and LLM services. The role focuses on designing, implementing and running the infrastructure platform that supports those AI services, so you would sit close to both platform engineering and applied AI delivery rather than in a purely generic DevOps seat.

The stack is Kubernetes in production, Linux and networking, GitOps and CI/CD pipelines with artifact and container registry management, plus GPU management in production covering scheduling and resource sharing. You would also work on model serving and monitoring of inference services, with nice-to-haves including vLLM, LiteLLM, Python, Go, Bash, MLOps and LLMOps practices, API gateways, Terraform and major cloud providers.

Highlights

• Hybrid setup with one day per week on site in Lodi
• Enterprise AI and LLM service delivery, not internal tooling only
• Production GPU scheduling and model serving ownership
• Advertised RAL between 35,000 and 40,000 euro