SRE Lead
Core
End-to-end ownership of infrastructure reliability, observability, automation, and production engineering for a distributed inference platform serving large language models.
Role type
Senior IC SRE Lead (Infrastructure & Platform)
Builds
Distributed inference platform for large language models
Domain
Cloud-native infrastructure, Kubernetes, AI/ML inference
Deliverable
infrastructure
Required skills
Kubernetes, Terraform, Infrastructure as Code, CI/CD pipeline design, Linux, networking, Prometheus/Grafana, Python/Go/Bash scripting, SLIs/SLOs/SLAs, incident management, technical leadership
Preferred skills
AI/ML or HPC workloads, GPU infrastructure, multi-cloud experience, service mesh, distributed tracing
Technologies
Kubernetes, Terraform, Helm, Ansible, Prometheus, Grafana, VictoriaMetrics, ELK/EFK, Python, Go, Bash
Responsibilities
Design resilient infrastructure for distributed workloads, optimize Kubernetes clusters and resource utilization, build automated CI/CD pipelines, establish observability strategy and alerting, define SRE standards and error budgets, lead incident response and post-mortems, mentor engineers and set technical direction
Seniority
Senior, hands-on IC with leadership responsibilities