We are seeking a skilled Engineer specializing in AI and MLOps to maintain and support machine learning applications in on-premises environments. This role involves managing Kubernetes clusters, collaborating on model deployment, and ensuring system health through robust monitoring. You will be instrumental in automating operational tasks and upholding best practices in security and performance for our ML infrastructure.

Key responsibilities include maintaining ML applications on Windows and Linux servers, managing Kubernetes clusters for ML workloads, and collaborating with data scientists for efficient model deployment.

You will implement and maintain monitoring solutions using DataDog, debug production issues with Python, and automate operational tasks to enhance system reliability.

Ensuring adherence to security, performance, and availability best practices, along with documenting system architecture and troubleshooting guides, are also core aspects of this role.

We require proven experience with Windows and Linux production environments, alongside hands-on management of on-premises servers, Kubernetes, and Docker containers.

Strong Python proficiency, a deep understanding of machine learning workflows, and experience in ML deployment development, including end-to-end model serving pipelines, are essential.

Familiarity with monitoring tools like DataDog, troubleshooting complex distributed systems, CI/CD for ML, AWS cloud platforms, and a background in Site Reliability Engineering or DevOps practices are also necessary. Excellent problem-solving and communication skills are paramount.