Platform Engineer – OpenShift+ AI-ML SRE | 4+ years

Cisco — Bangalore, India

Meet the Team You will be pivotal in contributing to the team responsible for designing and developing the next generation of scalable Kubernetes infrastructure with machine learning platforms that support both traditional ML and state-of-the-art Large Language Models (LLMs). This is a position for expert engineers where you will lead the technical direction, ensuring the performance, reliability, and scalability of AI systems while collaborating closely with data scientists, researchers, and other engineering teams. Your Impact The ideal candidate will have strong hands-on expertise in Red Hat OpenShift , proficiency in Golang and/or Python , and a passion for delivering highly reliable, scalable, and secure infrastructure. Hands on experience to AI technologies such as Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) & GPU frameworks. Core Responsibilities Design, deploy, administer, and optimize highly available Red Hat OpenShift platforms. Implement and drive Site Reliability Engineering (SRE) practices to ensure platform reliability, scalability, and operational excellence. Develop automation tools, operators, and platform services using Golang and/or Python . Manage cluster lifecycle activities including upgrades, patching, capacity planning, and performance tuning. Build and maintain CI/CD pipelines and Infrastructure as Code (IaC) solutions. Implement and maintain observability solutions including logging, metrics, tracing, and alerting. Monitor platform health and proactively identify and resolve reliability and performance issues. Solve production incidents, perform root cause analysis (RCA), and drive preventive actions. Collaborate closely with application and DevOps teams to improve deployment processes and platform adoption. Ensure platform security, compliance, and consistency to organizational standards and procedures. Participate in 16×5 on-call support rotation , providing timely response and resolution for production incidents an

View on HireSetu