Member of Technical Staff, AI Infrastructure Reliability

The role

You will work across cloud infrastructure, AI systems, and product teams to ensure platform components fit together, fail gracefully, and hold up under load. You will define reliability standards, own the reliability toolchain, and manage incidents.

What you will do

• Define reliability standards including SLOs, error budgets, and production readiness criteria.
• Own the reliability toolchain including logging, telemetry, alerting, failure injection, and automation.
• Ensure customer experience by addressing failures that occur even when systems are within SLO.
• Identify and fix failures occurring between systems.
• Run incident management, coordinate live production issues, and run blameless postmortems.
• Reduce toil by automating repetitive operational work.
• Partner across the organization with cloud infrastructure, inference, training, performance, and product teams.

Required 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.
• Operating and debugging Kubernetes, Terraform, and Docker in high-throughput production.
• High-throughput control planes, microservices, or multi-region setups.
• Fault-tolerant design, SLO/SLA management, automated failover, high-availability architecture.
• Ability to influence other teams to adopt standards through credibility and tooling.
• Willingness to dig into unfamiliar parts of the stack.
• Bachelor's or Master's in Computer Science, Computer Engineering, or equivalent practical experience.

Nice to have

• Observability tooling: Prometheus, Grafana, OpenTelemetry, and alerting people actually act on.
• GPU and ML infrastructure exposure: GPUs, inference serving, or distributed training.
• AI-assisted operations: Building agents or LLM-based tooling for investigation, triage, or automation.
• Open source background: Contributions to infrastructure, systems, or ML serving projects.
• Startup agility: Comfortable where pragmatism and teamwork matter more than process.

About the company

Fireworks is a Series D company providing a platform for specialized intelligence to build, train, and serve AI models. The company is valued at $17.5 billion and is backed by several investors including NVIDIA and Sequoia Capital.