Senior Site Reliability Engineer (AI/ML Platform)

LinkGroup is hiring for a role specializing in large-scale AI/ML infrastructure and services.

• Proven experience as a Site Reliability, Platform, or Infrastructure Engineer managing large-scale distributed systems.
• Deep practical experience with Kubernetes and container orchestration under heavy load.
• Hands-on expertise with observability tools including Prometheus, Grafana, and distributed tracing.
• Strong programming skills in Python, Go, and infrastructure-as-code tooling such as Terraform.
• Knowledge or experience with AI/ML infrastructure challenges, including model serving, inference engines, or GPU workloads.
• Proactive problem-solving attitude with ownership of issues through resolution and prevention.
• Collaborative mindset with experience mentoring engineers on SRE principles.

• Design and implement comprehensive observability using telemetry, dashboards (Grafana), and alerting (Prometheus).
• Define and track SLOs/SLIs to maintain service reliability.
• Automate manual tasks by writing code in Python and Go to create self-healing systems and tooling.
• Lead incident response, participate in on-call rotations, and conduct post-mortems.
• Build and maintain a CI/CD ecosystem with automated safety checks and rollback capabilities.
• Partner with product teams to advise on reliability and operational best practices.