Member of Technical Staff, Site Reliability Engineer

Inferact•San Francisco, CA

19h•Hybrid

About The Position

Inferact's mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and faster. Founded by the creators and core maintainers of vLLM, we sit at the intersection of models and hardware, a position that took years to build. We're looking for a Site Reliability Engineer to help make vLLM-powered inference systems reliable, observable, and operationally simple at production scale. This role is for someone who thinks about failure before launch, designs systems that are easier to operate, and knows how to turn incidents into durable improvements rather than one-off fixes. You'll work across engineering and infrastructure to define SLOs, improve monitoring and alerting, strengthen incident response, drive post-mortems, and reduce operational risk before it reaches users. Your work will directly impact the reliability, availability, and production readiness of the systems powering AI inference at scale.

Requirements

Bachelor's degree or equivalent experience in computer science, engineering, systems, infrastructure, or similar.
Strong experience operating production systems with meaningful traffic, user impact, or infrastructure criticality.
Deep understanding of SLOs, SLIs, error budgets, alerting, incident response, and post-mortem processes.
Strong Linux, networking, systems debugging, observability, and distributed systems fundamentals.
Strong programming or scripting ability in Python, Go, Bash, or similar for automation, tooling, and reliability improvements.

Nice To Haves

Experience supporting ML infrastructure, inference systems, GPU workloads, Kubernetes-based platforms, or high-scale backend services.
Experience building or improving observability systems using metrics, logs, traces, dashboards, alerts, and runbooks.
Experience with Kubernetes, Docker, Terraform, cloud infrastructure, service meshes, CI/CD systems, or production deployment platforms.
Experience driving incident review culture, post-mortem processes, reliability reviews, and prevention-oriented engineering work.
Owned reliability for high-throughput, latency-sensitive, or mission-critical production systems.
Supported AI inference, model serving, GPU clusters, ML platforms, or distributed serving infrastructure.
Built automation that reduced toil, improved recovery time, or prevented repeat incidents.
Led incident response for severe outages with clear communication across engineering and leadership.
Created practical SLOs, dashboards, alerts, runbooks, or release gates that improved production reliability.

Responsibilities

Define SLOs, improve monitoring and alerting, strengthen incident response, drive post-mortems, and reduce operational risk.
Live-fighting major production incidents, including mitigation, root cause analysis, escalation, and follow-through on prevention work.
Design operationally simple systems and identify likely failure modes before launch.
Partner with engineering teams to improve service design, release safety, capacity planning, and operational readiness.