Senior AI Infra SRE — GPU Cloud Reliability Leader

deCircle; San Francisco (CA); On-site; USD 120,000 - 150,000; Full time

Job summary

deCircle is seeking a Site Reliability Engineer based in San Francisco to ensure operational excellence for our GPU marketplace and AI infrastructure. The role involves defining service level objectives, managing capacity for a distributed system, and ensuring security protocols are adhered to. Candidates should have a strong background in reliability engineering, capacity planning, and incident response, with an emphasis on developing resilient infrastructures. Join us to contribute to our mission of making AI accessible and affordable globally.

Qualifications

• Expert in site reliability engineering with proven experience defining, monitoring, and maintaining SLOs.
• Strong background in capacity planning and management for distributed systems.
• Experienced in incident response and post‑mortem processes.
• Knowledge of deployment systems including progressive rollouts and automated rollback.
• Proficient in observability tools and practices such as metrics, logging, and tracing.

Responsibilities

• Ensure reliability, performance, and security of GPU marketplace and AI infrastructure.
• Define and maintain service level objectives for job success rates.
• Build robust incident response systems and manage capacity across distributed GPU network.
• Implement security and compliance frameworks to protect the infrastructure.

Skills

Site Reliability Engineering

Capacity Planning

Incident Response

Deployment Systems Knowledge

Observability Tools

Infrastructure Security

Secrets Management

Problem-Solving

Automation Mindset

Tools

Prometheus

Grafana

ELK Stack

Job description

deCircle is seeking a Site Reliability Engineer based in San Francisco to ensure operational excellence for our GPU marketplace and AI infrastructure. The role involves defining service level objectives, managing capacity for a distributed system, and ensuring security protocols are adhered to. Candidates should have a strong background in reliability engineering, capacity planning, and incident response, with an emphasis on developing resilient infrastructures. Join us to contribute to our mission of making AI accessible and affordable globally.