Site Reliability Engineer

CodeRound is hiring for this role.

Bengaluru · Onsite · Full-time · ₹15-25L · 4+ yrs

Join a fast-growing GenAI startup as an SRE and take ownership of the reliability, scalability, and operational excellence of a platform powering the end-to-end ML lifecycle. This is an infrastructure-heavy role: you will go deep on Kubernetes, Linux, cloud infrastructure, observability and production incidents, while supporting GPU and model-serving workloads and helping build strong SRE and incident-management practices.

What you'll do

Must have

Experience in SRE, DevOps, or Platform/Infrastructure engineering (infrastructure-heavy work, not application development) Strong hands-on Kubernetes in production (non-negotiable): has operated clusters, handled upgrades, ingress/networking, autoscaling and scheduling, and debugged pod, node, and network failures Strong Linux and networking fundamentals Production reliability and incident response: on-call, L1 analysis, RCA, postmortems, and observability (Prometheus, Grafana, Loki or similar) Hands-on Terraform, Helm, and CI/CD Experience with AWS, GCP, or Azure Scripting/programming in Python, Bash, or Go Can explain in depth every tool and metric on the resume

Good to have

Experience with MLOps / AI infrastructure Exposure to GPU clusters and model serving (vLLM, Triton or similar) Kubernetes cost optimisation and capacity planning Knowledge of release engineering Visible learning drive: strong fundamentals and curiosity can offset partial Kubernetes depth

Apply for this role on CodeRound AI