AI Infrastructure Reliability Engineer
Posted Updated
Description
Fireworks AI is seeking an experienced Reliability Engineer to join our team. You will own the reliability toolchain, define SLOs, run incident management, and automate toil while collaborating with cloud infra, AI systems, and product teams.
You will instrument systems, build logging/telemetry, manage failure budgets, and drive fixes across services. This role requires strong Linux, Python/Go/C++, Kubernetes, Terraform, Docker, and observability tooling experience.
Define reliability standards with SLOs, error budgets, and production readiness. Own the reliability toolchain: logging, telemetry, alerting, and failure testing. Maintain customer experience by ensuring services meet SLOs under load. Identify cross-system failure points and drive fixes across teams. Run incident management and postmortems; track follow-ups to completion. Automate repetitive operational tasks to reduce on-call toil. Collaborate with cloud infra, AI systems, and product teams on reliability. 5+ years in Linux internals, performance, and networking fundamentals. 5+ years in Python, Go, C++, or Rust for production-grade tooling. Experience with Kubernetes, Terraform, Docker in high-throughput environments. Strong reliability design with SLO/SLA management and automated failover.Skills
Sign in to read and join the discussion.