About the role

Role Overview

Site Reliability Engineer II focused on automating, monitoring, and maintaining the reliability of AI inference workloads on a cloud platform. The role aims to reduce operational toil, improve stability, and support continuous deployment while ensuring AI application availability and performance.

Responsibilities

Build and maintain dashboards, alerts, and monitoring for inference workloads using the existing observability stack
Develop reliability automation and tooling in Python or Go to reduce manual effort
Create and improve runbooks for inference-specific operations
Support SLO tracking and reporting to identify reliability trends and improvement opportunities
Maintain CI/CD pipelines, deployment safety checks, and rollback processes
Collaborate with product engineering teams to troubleshoot complex issues across the stack
Participate in on-call rotations, respond to production incidents, and run blameless post-mortems

Requirements

2+ years of Site Reliability Engineering experience and a Bachelor’s degree (or equivalent)
Proficiency in Python or Go for automation scripting
Experience with Linux systems administration and infrastructure troubleshooting
Familiarity with Kubernetes and containerization
Experience with observability tools such as Prometheus or Grafana
Exposure to CI/CD pipelines and infrastructure-as-code tools like Terraform or SaltStack
Curiosity and willingness to learn about AI infrastructure and distributed systems

Compensation & Benefits

US base salary range: $95,000–$171,000 per year (depending on experience, skills, certifications, and location)
Additional incentives may include annual bonuses, equity awards, and an ESPP
Healthcare, 401K, holidays and PTO, sick leave, parental leave, and employee assistance program
Flexible work arrangements: remote or office within the advertised country

About RemoteHunter

The employer operates in cloud computing and AI infrastructure, helping customers run AI inference models and enabling developers to build AI applications. It designs, implements, deploys, and operates AI platforms using scalable serverless inference workloads, GPU infrastructure, and Kubernetes to deliver reliable AI services at scale.