Tech Site Reliability Engineer

We are seeking a highly motivated and experienced Site Reliability Engineer to join our growing AI Model Operations team to help build, maintain, and monitor a portfolio of products for AI operations in UBS.
As an SRE, you will play a crucial role in ensuring the reliability, performance, and scalability of our production systems. You will find opportunities to improve our production reliability, applying software engineering principles to infrastructure and operations problems. own the reliability of central AI models and agents registry, deployment pipelines, AI SecOps products, and other products in our portfolio ensure the quality, security, reliability, and compliance of solutions by applying SRE best practices own incident management, root cause analysis, and implement preventative measures. support capacity, disaster recovery planning, and cost management collect and analyze operational data and identify SLI s from key metrics to define achievable SLO s for the product set collaborate with data scientists and other stakeholders to collect feedback and incorporate it into solutions automate processes leveraging predictive monitoring, auto-scaling, or self-healing apply performance analysis, log analytics, automated testing and communicate areas for improvement hands-on cloud experience utilizing both the cloud portal & CLI to deploy, monitor, troubleshoot and enhance services that our products rely upon. (Azure preferred) plotting metrics and creating dashboards to monitor service health identifying signals from logs or metrics and creating appropriate alerts experience working with the Azure and 3rd party APIs to develop automation/scripts or return data about Azure services experience working with Azure and proficiency in running container workloads identify cloud cost optimizations whilst balancing reliability and availability of services experience with managing and operating cloud workspaces (e.g. Databricks) proficiency with a high-level software language. (Python preferred), experience with DevOps. (Gitlab preferred)