We are seeking a skilled Site Reliability Engineer (SRE) to design, operate, and scale the high-performance infrastructure powering next-generation Generative AI (GenAI) platforms. The role will focus on ensuring the reliability, availability, scalability, and performance of production infrastructure, with particular emphasis on Kubernetes, GPU-enabled environments, and model-serving platforms.
The ideal candidate will have strong hands-on experience managing production Kubernetes clusters, troubleshooting complex infrastructure issues, automating operational workflows, and maintaining highly available cloud environments. This is an infrastructure-focused engineering position requiring expertise in SRE practices, DevOps, Linux, networking, observability, and infrastructure automation rather than application development.
You will take end-to-end ownership of critical production systems, drive reliability improvements, and build the infrastructure foundation required to support scalable AI workloads.
▪Build and maintain monitoring systems, alerts, dashboards, and operational visibility tools.
▪Implement observability practices using Prometheus, Grafana, Loki, or equivalent platforms.
▪Monitor system health, resource consumption, service availability, and infrastructure performance.
▪Define reliability metrics and establish appropriate service-level objectives (SLOs).
▪Continuously optimize infrastructure performance, availability, and operational efficiency.
6. Capacity Planning & Disaster Recovery
▪Conduct infrastructure capacity planning to support growing workloads and increasing compute requirements.
▪Develop and maintain disaster recovery strategies and infrastructure resilience mechanisms.
▪Identify scalability requirements and plan infrastructure improvements proactively.
▪Ensure production systems can handle workload fluctuations and unexpected failures.
Must-Have Skills & Qualifications
▪Experience in Site Reliability Engineering, DevOps, Platform Engineering, or Infrastructure Engineering.
▪Strong hands-on experience operating and maintaining Kubernetes clusters in production environments.
▪Practical knowledge of Kubernetes upgrades, ingress, networking, autoscaling, scheduling, and cluster troubleshooting.
▪Strong Linux administration and system troubleshooting skills.
▪Solid understanding of networking fundamentals, including DNS, TCP/IP, load balancing, and connectivity troubleshooting.
▪Experience with production incident management, on-call support, root cause analysis, and postmortems.
▪Hands-on experience with Terraform, Helm, and CI/CD pipelines.
▪Familiarity with observability and monitoring tools such as Prometheus, Grafana, and Loki.
▪Experience working with cloud infrastructure on AWS, GCP, or Microsoft Azure.
▪Strong automation and scripting capabilities.
Good-to-Have Skills
▪Experience managing GPU infrastructure and high-performance computing environments.
▪Familiarity with GenAI infrastructure, model-serving platforms, and AI/ML workloads.
▪Experience optimizing Kubernetes clusters for compute-intensive workloads.
▪Knowledge of container runtimes, service meshes, and distributed systems.
▪Experience designing highly available and fault-tolerant infrastructure architectures.
▪Understanding of disaster recovery planning and infrastructure security best practices.
Ideal Candidate Profile
The ideal candidate is an infrastructure-focused engineer who has independently operated production Kubernetes environments and understands the operational challenges of maintaining reliable, scalable platforms. They should be comfortable handling production incidents, troubleshooting issues across infrastructure layers, and implementing automation to improve system reliability.
Candidates with experience supporting GPU workloads, AI infrastructure, and model-serving platforms will have an added advantage.