Production SRE for AI Inference Platform

RiseMe; San Francisco (CA); On-site; USD 200,000 - 400,000; Full time

Benefits offered by this job

Health benefits

401(k) match

Equity

Job summary

Inferact seeks a Site Reliability Engineer to make vLLM-powered inference services dependable in production. You will own reliability across the production lifecycle, defining SLOs, building monitoring, and automating operational work.

You will drive incident mitigation, coordinate escalation, and lead post-mortems with concrete prevention actions, while partnering with engineering on capacity planning to enable scalable growth.

Qualifications

• Bachelor's degree or equivalent in CS/engineering or related field.
• Hands-on experience with production distributed systems and cloud infrastructure.
• Strong programming/scripting in Python/Go/Bash for automation.
• Experience handling major production incidents and post-mortems.

Responsibilities

• Own reliability across the production lifecycle, from release safety to observability.
• Define SLOs and build monitoring to pinpoint failures and automate recurring tasks.
• Drive incident mitigation, escalation, and post-mortems with concrete preventive actions.
• Collaborate with engineering on capacity planning and operational readiness for growth.

Skills

Python

Go

Bash

SRE concepts

Incident response

Linux basics

Networking

Diagnostics & debugging

Communication

Education

Bachelor's degree or equivalent experience

Tools

Kubernetes

Docker

Terraform

Job description

Inferact seeks a Site Reliability Engineer to make vLLM-powered inference services dependable in production. You will own reliability across the production lifecycle, defining SLOs, building monitoring, and automating operational work.

You will drive incident mitigation, coordinate escalation, and lead post-mortems with concrete prevention actions, while partnering with engineering on capacity planning to enable scalable growth.