Jobs → Engineering → SRE Engineer

About the Role We are looking for an SRE Engineer to join our team. This role focuses on building automation to help the platform achieve a 99.9% service-availability target. Key Responsibilities • Build automation for platform progress toward 99.9% service-availability • Improve telemetry and alerting for various metrics including latency, token throughput, and GPU utilization • Establish repeatable model benchmarks, stress tests, and SLO-based readiness checks • Improve autoscaling, model cold-start behavior, and incident remediation • Automate production operations including health and security checks • Improve AWS and GPU cost attribution and capacity reporting • Contribute to centralized identity, authorization, and auditability • Support model onboarding and hosting work Requirements • Experience with automation and system reliability engineering • Strong understanding of telemetry and alerting systems • Knowledge of benchmarking and capacity planning • Experience with autoscaling and deployment strategies • Familiarity with AWS and cloud cost management • Understanding of identity and authorization systems