Senior Reliability Engineer, AI Infrastructure

Fireworks; San Mateo; On-site; PHP 900,000 - 1,300,000; Full time

Job summary

Fireworks is seeking a Reliability Engineer to ensure the platform runs reliably as it scales. You will define SLOs, own the reliability toolchain, and coordinate incident response across cloud infra, AI systems, and product teams.

You’ll tackle failures that span multiple services, drive automation to reduce toil, and work with cross-functional teams to uphold production readiness and high availability. A strong foundation in distributed systems and modern open models is essential.

Qualifications

• 5+ years with Linux internals, system performance troubleshooting, and networking fundamentals (TCP/IP, HTTP, gRPC).
• 5+ years in Python, Go, C++, or Rust, writing production-grade tools and systems code.
• Cloud-native operations: Kubernetes, Terraform, and Docker in high-throughput production.
• Distributed systems: High-throughput control planes, microservices, or multi-region setups.
• Reliability fundamentals: Fault-tolerant design, SLO/SLA management, automated failover, HA architecture.
• Education: Bachelor's or Master's in CS/CE or equivalent practical experience.

Responsibilities

• Define reliability standards: SLOs, error budgets, production readiness criteria, instrumentation of systems.
• Own the reliability toolchain: Logging and telemetry pipelines, alerting standards, failure injection, load testing, automation.
• Keep customer experience from falling through the cracks: Ensure per-service reliability aligns with overall SLOs.
• Own the seams: Identify cross-system failures, manage retries, timeouts, and dependencies.
• Run incident management: Coordinate live production issues and postmortems.
• Reduce toil: Automate repetitive operational work.
• Partner across the org: Align cloud infra, AI serving, and product control planes on reliability.

Skills

Linux internals

Python

Go

C++

Rust

Networking fundamentals

SRE practices

Education

Bachelor's or Master's in CS/CE or equivalent

Tools

Kubernetes

Docker

Terraform

OpenTelemetry

Prometheus

Job description

Fireworks is seeking a Reliability Engineer to ensure the platform runs reliably as it scales. You will define SLOs, own the reliability toolchain, and coordinate incident response across cloud infra, AI systems, and product teams.

You’ll tackle failures that span multiple services, drive automation to reduce toil, and work with cross-functional teams to uphold production readiness and high availability. A strong foundation in distributed systems and modern open models is essential.