Staff Reliability Engineer for AI Infrastructure

Socket.dev; San Mateo (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Fireworks AI is seeking a Reliability Engineer to own the bar for platform reliability across cloud infrastructure, AI systems, and product teams. You will define SLOs, lead incident response, and drive improvements that keep services fast, available, and dependable across the stack.

You will work across Linux, container platforms, and distributed systems, building automation and observability that scales with growth.

Qualifications

• 5+ years Linux internals, performance troubleshooting, and networking fundamentals.
• 5+ years in Python, Go, C++, or Rust, building production-grade tools.
• Experience with Kubernetes, Terraform, and Docker in high-throughput production.
• Distributed systems focus with fault-tolerant design and SLO/SLA management.
• Bachelor's or Master's in CS, CS Engineering, or equivalent practical experience.

Responsibilities

• Define reliability standards: SLOs, error budgets, production readiness criteria.
• Own the reliability toolchain: Logging and telemetry pipelines, alerting, failure injection, load testing, automation.
• Keep customer experience by ensuring per-service reliability and accountability.
• Own seams between systems; identify and fix cross-service failure modes.
• Run incident management: coordinate live issues, postmortems, and follow-ups.
• Reduce toil through automation and scalable observability.
• Partner across org on capacity, multi-region risk, and serving/training stacks.

Skills

Linux internals

Performance troubleshooting

Networking fundamentals

Python

Go

C++

Rust

Kubernetes

Terraform

Docker

Distributed systems

SRE / Reliability

Education in CS

Education

Bachelor's or Master's in Computer Science or related field

Tools

Prometheus

Grafana

OpenTelemetry

LLM-based tooling

Git

Job description

Fireworks AI is seeking a Reliability Engineer to own the bar for platform reliability across cloud infrastructure, AI systems, and product teams. You will define SLOs, lead incident response, and drive improvements that keep services fast, available, and dependable across the stack.

You will work across Linux, container platforms, and distributed systems, building automation and observability that scales with growth.