Member of Technical Staff, Production Site Reliability Engineer
Core
Build dependable production inference services for vLLM-powered AI systems, ensuring reliability from release to recovery.
Role type
Senior IC Site Reliability Engineer (AI inference)
Builds
vLLM-powered AI inference services
Domain
AI inference, distributed systems, cloud infrastructure
Deliverable
production ML models (via careerplan.io/jobs/ad992ead-2a9a-4694-8fca-0504354548cd-member-of-technical-staff-production-site-reliability-engineer-at-inferact)
Required skills
Python, Go, Bash, Linux, networking, systems debugging, incident response, SLO/SLI definition, observability, automation, capacity planning
Preferred skills
Kubernetes, Docker, Terraform, GPU workload management, multi-tenant environments, deployment safety automation
Technologies
vLLM, Kubernetes, Docker, Terraform
Responsibilities
Define SLOs around availability, latency, and inference success; build monitoring to pinpoint failures; automate operational work; lead incident response and post-mortems; partner on capacity planning and operational readiness
Seniority
Senior, hands-on IC
