Staff AI Reliability Engineer — Infrastructure & SLOs

Fireworks AI, Inc.; New York, Northern (NY, KY); Hybrid; USD 140,000 - 190,000; Full time

Job summary

Fireworks AI, Inc. is seeking a Senior Reliability Engineer to own platform reliability across Linux-based systems, cloud infra, and AI workloads. You will define SLOs, oversee the tooling stack, and coordinate incident response across teams.

Join a fast-growing infrastructure team building open-model serving, zero-downtime rollouts, and automated fault-tolerance. This role emphasizes ownership, observability, and impact with a practical, startup-friendly environment.

Qualifications

• 5+ years with Linux internals, system performance troubleshooting, and networking fundamentals.
• 5+ years in Python, Go, C++, or Rust, writing production-grade tools and systems code.
• Cloud-native operations with Kubernetes, Terraform, and Docker in high-throughput production.
• Experience with distributed systems and multi-region setups.
• Education: Bachelor's or Master's in CS/CE or equivalent experience.

Responsibilities

• Define reliability standards: SLOs, error budgets, production readiness criteria.
• Own the reliability toolchain: logging, telemetry, alerting, and automation.
• Protect customer experience by ensuring per-service reliability and quick fixes.
• Identify seams between systems and drive cross-team fixes.
• Lead incident management: blameless postmortems and follow-ups.
• Reduce toil by automating repetitive operational work.
• Partner across the org on capacity, failure modes, and zero-downtime rollouts.

Skills

Linux internals

Performance troubleshooting

Networking fundamentals

Python

Go

C++

Rust

Open-source tooling

Observability

Distributed systems

SRE practices

Education

Bachelor's or Master's in Computer Science/Engineering

Tools

Kubernetes

Terraform

Docker

Prometheus

Grafana

OpenTelemetry

Job description

Fireworks AI, Inc. is seeking a Senior Reliability Engineer to own platform reliability across Linux-based systems, cloud infra, and AI workloads. You will define SLOs, oversee the tooling stack, and coordinate incident response across teams.

Join a fast-growing infrastructure team building open-model serving, zero-downtime rollouts, and automated fault-tolerance. This role emphasizes ownership, observability, and impact with a practical, startup-friendly environment.