Member of Technical Staff, Production Site Reliability Engineer

Inferact•San Francisco, CA

20d•$200,000 - $400,000•Hybrid

About The Position

Inferact is seeking a Site Reliability Engineer to ensure the dependability of Inferact's vLLM-powered inference services in production. This role involves working closely with platform engineers to integrate a reliability perspective into system design, deployment, and operation. The ideal candidate will proactively identify potential failures, streamline operations, and develop software to enable reliable, large-scale inference. Responsibilities include managing reliability throughout the production lifecycle, encompassing release safety, observability, incident response, and recovery. This involves defining SLOs for availability, latency, and successful inference requests, building effective monitoring tools, and automating routine operational tasks. During incidents, the engineer will lead mitigation efforts, coordinate escalations, and conduct post-mortems to implement preventative measures. Collaboration with engineering teams on capacity planning and operational readiness is also key to ensure scalable and manageable platform growth.

Requirements

Bachelor's degree or equivalent experience in computer science, engineering, systems, infrastructure, or similar.
Hands-on experience building or operating production distributed systems, cloud infrastructure, or services where reliability has meaningful user or business impact.
Strong programming or scripting ability in Python, Go, Bash, or similar, with experience building tools and automation that solve operational problems.
Experience responding to significant production incidents, including mitigation, root cause analysis, escalation, and following corrective actions through to completion.
Practical understanding of service-level objectives (SLOs), service-level indicators (SLIs), error budgets, and alerting that distinguishes user-impacting failures from noise.
Strong Linux, networking, and systems debugging fundamentals, with the ability to investigate failures across application and infrastructure boundaries.
Clear communication, sound judgment under pressure, and the ability to work with engineering teams to identify failure modes and make systems simpler to operate.

Nice To Haves

Experience supporting AI inference, model serving, ML infrastructure, GPU workloads, or other latency-sensitive, high-throughput services.
Experience deploying, operating, and debugging Kubernetes-based services, with familiarity with Docker, Terraform, or comparable infrastructure tooling.
Experience building observability with metrics, logs, traces, dashboards, and actionable alerts across distributed systems.
Experience improving deployment safety and recovery through automation, testing, release gates, and rollback procedures.
Experience with resource scheduling, capacity planning, or workload isolation in multi-tenant cloud or GPU environments.
Owned reliability for an inference service or other mission-critical platform through a period of significant growth.
Built automation that measurably reduced operational toil, improved recovery time, or prevented repeat incidents.
Established practical SLOs, post-mortem processes, or production-readiness reviews that helped engineering teams ship with greater confidence.

Responsibilities

Own reliability across the production lifecycle, from release safety and observability to incident response and recovery.
Define SLOs around availability, latency, and successful inference requests.
Build monitoring that helps engineers pinpoint failures.
Automate recurring operational work.
Drive mitigation, coordinate escalation, and lead post-mortems when incidents occur.
Partner with engineering on capacity planning and operational readiness.