Member of Technical Staff, AI Infrastructure Reliability
Core
Ensure the reliability of Fireworks' AI inference and training platform serving 40 trillion tokens daily by defining standards, managing incidents, and automating operational toil.
Role type
Senior Reliability Engineer (AI Infrastructure)
Builds
Production-grade AI inference and training systems for open models
Domain
Cloud infrastructure, AI systems, and distributed computing
Deliverable
production ML models
Required skills
Linux internals, system performance troubleshooting, networking (TCP/IP, HTTP, gRPC), Python, Go, C++, or Rust, Kubernetes, Terraform, Docker, distributed systems, fault-tolerant design, SLO/SLA management
Preferred skills
Observability tooling (Prometheus, Grafana, OpenTelemetry), GPU and ML infrastructure exposure, AI-assisted operations, open source contributions
Technologies
Kubernetes, Terraform, Docker, Prometheus, Grafana, OpenTelemetry
Responsibilities
Define reliability standards (SLOs, error budgets), own the reliability toolchain (logging, alerting, failure injection), manage incident response and postmortems, reduce operational toil through automation, partner across cloud infrastructure and AI teams
Seniority
Senior, hands-on IC